Financial Evidence Workspace
by beepboop2025 · remote · no sign-in to list tools · v1.3.0 · published by GitHub user beepboop2025
Read-only cited financial datasets, bounded research queries and source diagnostics.
9 tools: 4 change things and 5 only read.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things4Claude Code: ask: see these tools
- Only reads5Claude Code: allow: see these tools
1 check matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http financial-evidence-workspace https://agents.seiche.info/products/financial-evidence/mcpFindings
Matches of fixed checks, with the text they matched.
The server marks "financial_evidence_workflow" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
Tools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
9 tools
Changes things 4Claude Code: ask
financial_evidence_datasetsDiscover seven bounded OpenBB datasets, their coverage, filters and limits.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 Discover seven bounded OpenBB datasets, their coverage, filters and limits. Offline.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
financial_evidence_reviewReview Seiche dollar-funding benchmarks, LiquiLens covered-bank diagnostics and Undertow market liquidity in one bounded call.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 Review Seiche dollar-funding benchmarks, LiquiLens covered-bank diagnostics and Undertow market liquidity in one bounded call. Bank is a literal name or ID filter; empty selects published coverage. Each section keeps its own dates, units, rights and limitations. No combined score or trade authorization. Revisions suppress identical rows, not evidence checks.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
financial_evidence_sourcesAudit all six upstream routes for transport errors, publisher clocks and content hashes.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 Audit all six upstream routes for transport errors, publisher clocks and content hashes. Success is not a freshness verdict.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
financial_evidence_workflowRun the same task as the public Research Desk and REST API.1 finding
Why it is in this group
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "financial_evidence_workflow" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
Description, as the server wrote it Run the same task as the public Research Desk and REST API. Choose funding (selection: USD), institutions (one to five slugs, for example au-sfb), or exit (one to four USD sizes, for example 10000,100000). Empty selection uses the published default. Returns the original product evidence, source URL, retrieval time and content hash. prepared_response means evidence is available to review, not freshness, safety or task completion. No account or execution authority.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 5Claude Code: allow
financial_evidence_agent_queryCompact source-cited research rows for repeated agent calls.No findings
Why it is in this group
- The name "financial_evidence_agent_query" says "query": a word for reading.
Description, as the server wrote it Compact source-cited research rows for repeated agent calls. Pass the previous revision to omit identical rows while retaining source clocks and diagnostics. Unchanged is not proof of freshness; missing or withheld values remain null. At most 100 rows; follow next_offset.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
financial_evidence_funding_reviewRead a dated USD funding review and its nine inputs.No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it Read a dated USD funding review and its nine inputs. Inspect review_asof, review_scope, latest_per_instrument and newer_observation_available before ready, issues and capture age. Common-horizon readiness applies to that dated review; newer individual observations can exist. Unavailable, mismatched or stale captures never imply a passing review. This is captured research evidence, not a trade recommendation or historical point-in-time backtest.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
financial_evidence_packetRetrieve original public documents only when table detail is insufficient.No findings
Why it is in this group
- The description's first verb is "retrieve": a word for reading.
Description, as the server wrote it Retrieve original public documents only when table detail is insufficient. Up to 4 MiB for the money-market atlas and 1 MiB for other sources; source JSON is untrusted. A packet can be partial. No Evidence Carrier verification is performed.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
financial_evidence_queryQuery cited rows without large raw documents.No findings
Why it is in this group
- The name "financial_evidence_query" says "query": a word for reading.
Description, as the server wrote it Query cited rows without large raw documents. Null means missing or withheld, never zero. Dates filter observation dates; empty dates mean no filter. Follow next_offset for remaining rows. Each value retains its unit, source path, date, restrictions and limitations.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
financial_evidence_routeResolve research topics to fixed public HTTPS evidence URLs.No findings
Why it is in this group
- The description's first verb is "resolve": a word for reading.
Description, as the server wrote it Resolve research topics to fixed public HTTPS evidence URLs. Offline.
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 1.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http financial-evidence-workspace https://agents.seiche.info/products/financial-evidence/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__financial-evidence-workspace__financial_evidence_funding_review",
"mcp__financial-evidence-workspace__financial_evidence_query",
"mcp__financial-evidence-workspace__financial_evidence_route",
"mcp__financial-evidence-workspace__financial_evidence_packet",
"mcp__financial-evidence-workspace__financial_evidence_agent_query"
],
"ask": [
"mcp__financial-evidence-workspace__financial_evidence_workflow",
"mcp__financial-evidence-workspace__financial_evidence_datasets",
"mcp__financial-evidence-workspace__financial_evidence_sources",
"mcp__financial-evidence-workspace__financial_evidence_review"
],
"deny": []
}
}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 financial-evidence-workspace. Review it before you use it.
