72hours security check

io.github.maebsy/72hoursmaebsystreamable-httpv1.1.0Scanned 1 hour ago

Scan a public GitHub repo, explain risks, get fix prompts and rescan to confirm fixes.

15 tools: 1 can delete or cancel things, 10 change things and 4 only read.

Reads private data · 1
Reads text others write · 6
Can send data out · 0
1 finding

Anlyon alternative

11 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

15 tools

Deletes or cancels 1Removes, cancels or revokes something.Claude Code: deny

close_workspaceRevoke this workspace and its result access.No findings
Why it is in this group
- The name "close_workspace" says "close": a word for a change.
- The description's first verb is "revoke": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it
Revoke this workspace and its result access. Does not cancel already submitted backend jobs.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false

Changes things 10Creates or changes something that can be changed back.Claude Code: ask

audit_repositoryOne call security audit of a PUBLIC GitHub repo the user is authorized to scan.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it
One call security audit of a PUBLIC GitHub repo the user is authorized to scan. Creates a workspace if workspace_token is empty (keep the returned token private), scans, waits up to 90 s, starts GPU analysis for the top max_analyses (0-5) findings and returns summary + next steps. Reuse request_id only for the SAME request.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
check_fixAfter fixes are PUSHED to the default branch: rescan the same repo against scan_id and list resolved, persisting, new and key-reissue-needed findings.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it
After fixes are PUSHED to the default branch: rescan the same repo against scan_id and list resolved, persisting, new and key-reissue-needed findings. Same commit means the fix was not pushed yet.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
create_workspaceCreate a private, expiring workspace.Reads text others writeNo findings
Why it is in this group
- The name "create_workspace" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it
Create a private, expiring workspace. Save its capability only in the user's AI conversation.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
generate_reportGenerate the service's report from owned server scan and available analyses, indicating incomplete work.1 finding
Why it is in this group
- The name "generate_report" says "generate": 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 "generate_report" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "generate_report" says "generate": a word for a change.
  What this check looks for
Description, as the server wrote it
Generate the service's report from owned server scan and available analyses, indicating incomplete work.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
incident_reportDraft only; NEVER submits.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
Draft only; NEVER submits. kind: assess/incident-24h/privacy-72h. incident requires discovered_at ISO time; optional organization {name,service_name,contact_email}, summary, incident_types, damage, actions_taken, personal_info {leaked: confirmed/suspected/none, affected_count, items}. Use only user-confirmed facts.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
rescanRescan the SAME repository default branch.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it
Rescan the SAME repository default branch. Only published changes are visible; unpushed edits are not.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
service_infoLearn the whole workflow and available service capabilities before creating work.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
Learn the whole workflow and available service capabilities before creating work.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
start_analysisStart GPU Red/Blue review of one real scan finding.Reads text others writeNo findings
Why it is in this group
- The name "start_analysis" says "start": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it
Start GPU Red/Blue review of one real scan finding. Same inputs deduplicate.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
start_scanStart a REAL public GitHub scan.Reads text others writeNo findings
Why it is in this group
- The name "start_scan" says "start": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it
Start a REAL public GitHub scan. User authorization required. Reuse request_id on identical retries.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
verify_demoRuntime proof on the DEMO target only: isolated sandbox replays attacks before/after the fix and runs functional tests.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
Runtime proof on the DEMO target only: isolated sandbox replays attacks before/after the fix and runs functional tests. mode: reference (human fix) or ai (Red/Blue generated attacks and fix). Not the user's repo. If a previous call returned status queued/running, pass its verify_job_id to keep polling the same job.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

Only reads 4Looks things up and changes nothing.Show 4 read-only tools

audit_statusScan summary, analysis statuses and which fix prompts (get_fix_prompt) are ready, in one call.No findings
Why it is in this group
- The name "audit_status" says "status": a word for reading.
Description, as the server wrote it
Scan summary, analysis statuses and which fix prompts (get_fix_prompt) are ready, in one call.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_analysisPoll GPU status and delivery gates; inference can take several minutes.No findings
Why it is in this group
- The name "get_analysis" says "get": a word for reading.
Description, as the server wrote it
Poll GPU status and delivery gates; inference can take several minutes. Never fake ready results.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_fix_promptGet a gated real LLM proposal.No findings
Why it is in this group
- The name "get_fix_prompt" says "get": a word for reading.
Description, as the server wrote it
Get a gated real LLM proposal. Agent must inspect code, check repo/commit, fix and test in its workspace.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_scanPoll every >=10 seconds; on done return actual commit, coverage and up to 50 LLM-input findings.Reads private dataNo findings
Why it is in this group
- The name "get_scan" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "commit": it reads repositories.
Description, as the server wrote it
Poll every >=10 seconds; on done return actual commit, coverage and up to 50 LLM-input findings.
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.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data1: Reads files, mail, messages, databases, secrets, calendars or repositories.; get_scan
Reads text others write6: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; audit_repository
check_fix
create_workspace
rescan
start_analysis
start_scan
Can send data out0: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Findings

Matches of fixed checks, with the text they matched.

1 warn

Warngenerate_report
The server marks "generate_report" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "generate_report" says "generate": a word for a change.
What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

All changes to this server

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http 72hours https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc

claude mcp add --transport http 72hours https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc

Run in a terminal.

Claude Code permissions

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

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__72hours__get_scan",
      "mcp__72hours__get_analysis",
      "mcp__72hours__get_fix_prompt",
      "mcp__72hours__audit_status"
    ],
    "ask": [
      "mcp__72hours__service_info",
      "mcp__72hours__create_workspace",
      "mcp__72hours__start_scan",
      "mcp__72hours__start_analysis",
      "mcp__72hours__rescan",
      "mcp__72hours__generate_report",
      "mcp__72hours__incident_report",
      "mcp__72hours__audit_repository",
      "mcp__72hours__check_fix",
      "mcp__72hours__verify_demo"
    ],
    "deny": [
      "mcp__72hours__close_workspace"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as 72hours. Review it before you use it.

Capability tags behind 7 rules

mcp__72hours__create_workspace untrusted-input
mcp__72hours__start_scan untrusted-input
mcp__72hours__get_scan private-data
mcp__72hours__start_analysis untrusted-input
mcp__72hours__rescan untrusted-input
mcp__72hours__audit_repository untrusted-input
mcp__72hours__check_fix untrusted-input

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://anlyon.dev/api/v1/servers/io.github.maebsy/72hours/verify?hash=44e596eeaf49e039f42e2160b72a020613c0b4449d705ac9daf110f6aa27f480" | jq -e '.changed == false'

Pinned hash 44e596eeaf49, from Oct 31, 2026, 22:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.maebsy/72hours/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

[![anlyon.dev](https://anlyon.dev/badge/io.github.maebsy/72hours.svg)](https://anlyon.dev/servers/io.github.maebsy/72hours)

Source: MCP Registry · repository. Synced Oct 31, 2026, 22:17 UTC.