Skip to content

ScrubMyText + Agent Infrastructure

by scrubmytext.com · remote · no sign-in to list tools · v7.5.0 · published by com.scrubmytext

49 deterministic tools for text integrity, agent control, and contextual quality evidence.

Deletes · 3Final · 1Changes · 37

49 tools: 3 can delete or cancel things, 1 do something that can't be undone, 37 change things and 8 only read.

Scanned Oct 21, 2026

3 checks matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http tools https://api.scrubmytext.com/mcp

Findings

Matches of fixed checks, with the text they matched.

3 info

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

49 tools

Deletes or cancels 3Claude Code: deny
  • cancel_approvalPaid: cancel a pending human approval request so its link can no longer approve the action.No findings

    Why it is in this group

    • The name "cancel_approval" says "cancel": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Paid: cancel a pending human approval request so its link can no longer approve the action.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
  • delete_signalPaid: immediately delete a signal inbox and all stored event bodies.No findings

    Why it is in this group

    • The name "delete_signal" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Paid: immediately delete a signal inbox and all stored event bodies.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
  • release_actionPaid: release an uncompleted action lock using its lock_id so another attempt can safely acquire it.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Paid: release an uncompleted action lock using its lock_id so another attempt can safely acquire it.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
Can't be undone 1Claude Code: ask
  • manage_context_statusPublish, inspect, supersede, dispute, or revoke digest-only context status so downstream agents can stop using stale inputs.No findings

    Why it is in this group

    • The name "manage_context_status" says "status": a word for reading.
    • The description's first verb is "publish": a word for a change that another call does not undo.
    Description, as the server wrote it
    Publish, inspect, supersede, dispute, or revoke digest-only context status so downstream agents can stop using stale inputs. Stores no context body and does not invalidate copies outside this service. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Changes things 37Claude Code: ask
  • anchor_context_traceCreate or inspect an immutable provenance anchor from a context digest, parent digests, and processing stage.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create or inspect an immutable provenance anchor from a context digest, parent digests, and processing stage. No context content is stored. Production; subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • check_agent_readinessDeterministically check a supplied MCP server card against a narrow, published integration contract.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Deterministically check a supplied MCP server card against a narrow, published integration contract. The service does not fetch arbitrary URLs and does not certify security or correctness. Free or paid.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • check_approvalPaid: check whether a human approval request is pending, approved, rejected, expired, or cancelled.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Paid: check whether a human approval request is pending, approved, rejected, expired, or cancelled.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • complete_actionPaid: mark the current lock completed and preserve the idempotency record for its configured retention period.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Paid: mark the current lock completed and preserve the idempotency record for its configured retention period.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • create_signalUse when an agent must wait for an external callback, webhook, job completion, or asynchronous event.No findings

    Why it is in this group

    • The name "create_signal" says "create": a word for a change.
    Description, as the server wrote it
    Use when an agent must wait for an external callback, webhook, job completion, or asynchronous event. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • detect_secretsUse before an agent logs, stores, or forwards text that may contain credentials.1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...ores, or forwards text that may contain credentials. Finds likely API keys, private keys, J..."

      What this check looks for
    Description, as the server wrote it
    Use before an agent logs, stores, or forwards text that may contain credentials. Finds likely API keys, private keys, JWTs, cloud credentials, and secret patterns without echoing values. Trial, subscription, or x402 pay-per-call.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • fingerprint_actionUse before retryable work to derive a stable SHA-256 action fingerprint and idempotency key from an action name, optional scope, and JSON arguments.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Use before retryable work to derive a stable SHA-256 action fingerprint and idempotency key from an action name, optional scope, and JSON arguments. Object key order does not affect the result. Returns no input values and stores nothing. Free or paid.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • lock_actionUse immediately before a consequential agent action to atomically claim an idempotency key so retries cannot execute it twice.No findings

    Why it is in this group

    • The name "lock_action" says "lock": a word for a change.
    Description, as the server wrote it
    Use immediately before a consequential agent action to atomically claim an idempotency key so retries cannot execute it twice. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • lock_action_intentUse immediately before a consequential retryable action when no stable idempotency key exists.No findings

    Why it is in this group

    • The name "lock_action_intent" says "lock": a word for a change.
    Description, as the server wrote it
    Use immediately before a consequential retryable action when no stable idempotency key exists. Deterministically fingerprints the action and arguments, atomically claims that key, and returns safe_to_execute. Repeat calls with equivalent object-key ordering return the same fingerprint and cannot acquire a second active lock. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • manage_action_challengeCreate, inspect, consume, or cancel a digest-bound cooling-off window.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create, inspect, consume, or cancel a digest-bound cooling-off window. A bearer challenger can veto before the deadline; afterward the owner can atomically consume one execution right during a bounded window. This is exception handling, not affirmative consent or legal approval. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • manage_action_compensationBind a compensating-action digest before execution, record that the primary action executed, and atomically mark compensation once.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Bind a compensating-action digest before execution, record that the primary action executed, and atomically mark compensation once. Stores digests only and does not perform either action. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • manage_action_quorumCreate, inspect, consume, or cancel an N-of-M bearer authorization quorum.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create, inspect, consume, or cancel an N-of-M bearer authorization quorum. Each unique bearer can decide once; only a successful one-time consume grants an execution right. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • manage_action_reconciliationOpen, inspect, append digest-only evidence to, or resolve a discrepancy between expected and observed action outcomes.No findings

    Why it is in this group

    • The description's first verb is "open": a word for a change.
    Description, as the server wrote it
    Open, inspect, append digest-only evidence to, or resolve a discrepancy between expected and observed action outcomes. Production; subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • manage_agent_escalationCreate, inspect, or cancel a digest-only incident with a private bearer operator link and deterministic response and resolution SLA state.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create, inspect, or cancel a digest-only incident with a private bearer operator link and deterministic response and resolution SLA state. Link delivery remains the caller’s responsibility. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • manage_agent_stopSet, inspect, or clear a durable stop signal for a hashed agent or workflow key.No findings

    Why it is in this group

    • The name "manage_agent_stop" says "stop": a word for a change.
    Description, as the server wrote it
    Set, inspect, or clear a durable stop signal for a hashed agent or workflow key. Callers should fail closed whenever stopped is true. Production; subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • manage_attention_budgetCreate, inspect, reserve, release, or close a finite review-capacity pool with per-subject caps, retry-safe reservations, and protected priority capacity.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create, inspect, reserve, release, or close a finite review-capacity pool with per-subject caps, retry-safe reservations, and protected priority capacity. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • manage_authority_delegationIssue, consume, inspect, or revoke a narrow bearer capability bound to one action fingerprint and a maximum use count.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Issue, consume, inspect, or revoke a narrow bearer capability bound to one action fingerprint and a maximum use count. This is a technical capability, not identity proof or a legal delegation. Production; subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • manage_context_rightsIssue, inspect, evaluate, or revoke a digest-bound machine-readable context-rights envelope.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Issue, inspect, evaluate, or revoke a digest-bound machine-readable context-rights envelope. It is a technical policy signal, not legal advice or proof of ownership. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • manage_disclosure_budgetCreate, inspect, record against, or close a cumulative disclosure budget with total, per-recipient, and per-category limits.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create, inspect, record against, or close a cumulative disclosure budget with total, per-recipient, and per-category limits. Stores hashes and counters, not disclosed content or recipient identities. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • manage_resource_leaseAtomically acquire, inspect, or release a short-lived exclusive lease on a hashed resource key.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Atomically acquire, inspect, or release a short-lived exclusive lease on a hashed resource key. Production; subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • manage_task_contractOffer, accept, inspect, complete, or cancel a digest-bound technical task commitment.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Offer, accept, inspect, complete, or cancel a digest-bound technical task commitment. This records service state; it is not a legal contract, escrow, payment, or identity verification. Production.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • manage_task_deadlineCreate, inspect, complete, or cancel a task deadline whose due and escalation state is derived from an independent server clock even when the agent is offline.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create, inspect, complete, or cancel a task deadline whose due and escalation state is derived from an independent server clock even when the agent is offline. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • manage_task_handoffCreate a bearer-token task handoff, let another paid API identity claim it exactly once, and inspect, complete, or cancel the transfer.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create a bearer-token task handoff, let another paid API identity claim it exactly once, and inspect, complete, or cancel the transfer. Only task fingerprints are stored. Production.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • manage_terms_pinPin, inspect, or revoke an immutable digest-bound record of observed terms, interface, version, and price.No findings

    Why it is in this group

    • The name "manage_terms_pin" says "pin": a word for a change.
    Description, as the server wrote it
    Pin, inspect, or revoke an immutable digest-bound record of observed terms, interface, version, and price. Stores bounded metadata and digests, not the terms body. This is technical evidence, not a legal agreement. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • match_policy_requirementsDeterministically compare bounded provider capabilities with consumer-required and forbidden policy tokens.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Deterministically compare bounded provider capabilities with consumer-required and forbidden policy tokens. Processes supplied tokens without storing policy content and does not make legal or compliance conclusions. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • prepare_for_agentUse as the default preprocessing step before an AI agent consumes untrusted external text.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Use as the default preprocessing step before an AI agent consumes untrusted external text. Returns agent-ready text plus inspection, risk-scan, and secret-detection reports. Trial, subscription, or x402 pay-per-call.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • record_action_receiptCreate or retrieve an immutable receipt digest for an action outcome without storing the action or outcome payload.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create or retrieve an immutable receipt digest for an action outcome without storing the action or outcome payload. Production; subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • record_quality_observationSubmit an opt-in structured observation for an exact target and task.1 finding

    Why it is in this group

    • The description's first verb is "submit": a word for a change.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...ons are E0. Stores no prompt, response, credential, email, or free-form review. Free verif..."

      What this check looks for
    Description, as the server wrote it
    Submit an opt-in structured observation for an exact target and task. Receipt-linked observations are labeled E1; other observations are E0. Stores no prompt, response, credential, email, or free-form review. Free verified contributor or subscription key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • redact_sensitive_textUse before storing, sharing, logging, or sending text downstream when it may contain credentials or identifiers.1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...ing text downstream when it may contain credentials or identifiers. Pattern-based redaction..."

      What this check looks for
    Description, as the server wrote it
    Use before storing, sharing, logging, or sending text downstream when it may contain credentials or identifiers. Pattern-based redaction; trial, subscription, or x402 pay-per-call.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • request_approvalUse when an agent needs independent human approval before a consequential action.No findings

    Why it is in this group

    • The name "request_approval" says "request": a word for a change.
    Description, as the server wrote it
    Use when an agent needs independent human approval before a consequential action. Creates a secure approval link. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • request_quality_correctionAttach a digest-only correction or appeal request to a quality card.No findings

    Why it is in this group

    • The name "request_quality_correction" says "request": a word for a change.
    Description, as the server wrote it
    Attach a digest-only correction or appeal request to a quality card. Requests are visible as unverified pending state and do not erase evidence or prove provider identity. Free verified contributor or subscription key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • reserve_action_budgetAtomically reserve integer units under a named, period-scoped ceiling.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Atomically reserve integer units under a named, period-scoped ceiling. A reservation_key makes retries idempotent. The service stores hashes and counters, not purchase details. Production; subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • rework_textUse when an agent needs a deterministic, no-LLM rewrite while preserving protected facts such as numbers, URLs, emails, and quotes.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Use when an agent needs a deterministic, no-LLM rewrite while preserving protected facts such as numbers, URLs, emails, and quotes. Returns change metrics and preservation checks; does not verify authorship or watermark status. Trial, subscription, or x402 pay-per-call.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • sanitize_agent_contextUse before putting untrusted retrieved or uploaded text into a model context.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Use before putting untrusted retrieved or uploaded text into a model context. Normalizes structural artifacts, returns risk signals, and can redact sensitive patterns. Trial, subscription, or x402 pay-per-call.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • scan_untrusted_textUse before an agent ingests pasted, retrieved, uploaded, or externally supplied text.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Use before an agent ingests pasted, retrieved, uploaded, or externally supplied text. Returns structural and heuristic risk signals; it does not determine maliciousness or safety. Trial, subscription, or x402 pay-per-call.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • scrub_textNormalize hidden/control characters and formatting artifacts without rewriting wording.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Normalize hidden/control characters and formatting artifacts without rewriting wording. Free or paid.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • verify_signed_signalVerify an HMAC-SHA256 signal, enforce timestamp freshness, and reject a replayed nonce.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Verify an HMAC-SHA256 signal, enforce timestamp freshness, and reject a replayed nonce. The message and shared secret are never stored. Production; subscription API key required.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Only reads 8Claude Code: allow
  • check_actionUse to inspect an idempotency key before or after an agent action.No findings

    Why it is in this group

    • The description's first verb is "inspect": a word for reading.
    Description, as the server wrote it
    Use to inspect an idempotency key before or after an agent action. Subscription API key required.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • compare_quality_targetsReturn contextual quality cards for two to ten exact targets in caller-provided order.No findings

    Why it is in this group

    • The name "compare_quality_targets" says "compare": a word for reading.
    Description, as the server wrote it
    Return contextual quality cards for two to ten exact targets in caller-provided order. It exposes evidence and uncertainty without producing a paid ranking or universal winner. Free.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • compare_textUse to verify what changed between two text versions and whether differences are only scrub/format artifacts.No findings

    Why it is in this group

    • The name "compare_text" says "compare": a word for reading.
    Description, as the server wrote it
    Use to verify what changed between two text versions and whether differences are only scrub/format artifacts. Trial, subscription, or x402 pay-per-call.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_quality_cardRetrieve a public, contextual quality card for an exact MCP server or REST API version.No findings

    Why it is in this group

    • The name "get_quality_card" says "get": a word for reading.
    Description, as the server wrote it
    Retrieve a public, contextual quality card for an exact MCP server or REST API version. Scores remain unavailable until at least three independent verified contributors submit structured observations. Free.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_signal_eventsPaid: retrieve events received by a temporary signal inbox in arrival order.No findings

    Why it is in this group

    • The name "get_signal_events" says "get": a word for reading.
    Description, as the server wrote it
    Paid: retrieve events received by a temporary signal inbox in arrival order.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • inspect_textInspect exact Unicode, invisible characters, normalization, and mixed-script anomalies.No findings

    Why it is in this group

    • The name "inspect_text" says "inspect": a word for reading.
    Description, as the server wrote it
    Inspect exact Unicode, invisible characters, normalization, and mixed-script anomalies. Free or paid.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_quality_cardsList exact service-version/task quality cards that have reached the public three-verified-contributor evidence threshold.No findings

    Why it is in this group

    • The name "list_quality_cards" says "list": a word for reading.
    Description, as the server wrote it
    List exact service-version/task quality cards that have reached the public three-verified-contributor evidence threshold. Results are ordered by recent evidence, not quality, payment, or sponsorship. Free.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • validate_outputUse immediately before a downstream action when model output must be valid JSON or match a schema.No findings

    Why it is in this group

    • The name "validate_output" says "validate": a word for reading.
    Description, as the server wrote it
    Use immediately before a downstream action when model output must be valid JSON or match a schema. Trial, subscription, or x402 pay-per-call.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 7.5.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http tools https://api.scrubmytext.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__tools__inspect_text",
      "mcp__tools__compare_text",
      "mcp__tools__validate_output",
      "mcp__tools__check_action",
      "mcp__tools__get_signal_events",
      "mcp__tools__list_quality_cards",
      "mcp__tools__get_quality_card",
      "mcp__tools__compare_quality_targets"
    ],
    "ask": [
      "mcp__tools__scrub_text",
      "mcp__tools__scan_untrusted_text",
      "mcp__tools__redact_sensitive_text",
      "mcp__tools__detect_secrets",
      "mcp__tools__sanitize_agent_context",
      "mcp__tools__prepare_for_agent",
      "mcp__tools__rework_text",
      "mcp__tools__fingerprint_action",
      "mcp__tools__lock_action",
      "mcp__tools__lock_action_intent",
      "mcp__tools__complete_action",
      "mcp__tools__create_signal",
      "mcp__tools__request_approval",
      "mcp__tools__check_approval",
      "mcp__tools__manage_action_challenge",
      "mcp__tools__reserve_action_budget",
      "mcp__tools__record_action_receipt",
      "mcp__tools__verify_signed_signal",
      "mcp__tools__manage_resource_lease",
      "mcp__tools__manage_authority_delegation",
      "mcp__tools__manage_agent_stop",
      "mcp__tools__manage_task_handoff",
      "mcp__tools__manage_action_reconciliation",
      "mcp__tools__anchor_context_trace",
      "mcp__tools__manage_task_contract",
      "mcp__tools__check_agent_readiness",
      "mcp__tools__manage_action_quorum",
      "mcp__tools__manage_task_deadline",
      "mcp__tools__manage_attention_budget",
      "mcp__tools__manage_agent_escalation",
      "mcp__tools__manage_terms_pin",
      "mcp__tools__match_policy_requirements",
      "mcp__tools__manage_action_compensation",
      "mcp__tools__manage_context_status",
      "mcp__tools__manage_context_rights",
      "mcp__tools__manage_disclosure_budget",
      "mcp__tools__record_quality_observation",
      "mcp__tools__request_quality_correction"
    ],
    "deny": [
      "mcp__tools__release_action",
      "mcp__tools__delete_signal",
      "mcp__tools__cancel_approval"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as tools. Review it before you use it.