Skip to content

Agora

by mo-grantsmith · remote · no sign-in to list tools · v0.1.0 · published by GitHub user mo-grantsmith

Find governed AI capabilities and verify signed receipts. Read-only, no account.

Changes · 2

3 tools: 2 change things and 1 only read.

Scanned Oct 21, 2026

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

claude mcp add --transport http agora https://agora-console-production.up.railway.app/mcp

Findings

Matches of fixed checks, with the text they matched.

1 info

Tools

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

3 tools

Changes things 2Claude Code: ask
  • execute_capabilityStart a declared capability through Agora's own governed summon path, and return the RECEIPT ID of the act.No findings

    Why it is in this group

    • The name "execute_capability" says "execute": a word for a change.
    Description, as the server wrote it
    Start a declared capability through Agora's own governed summon path, and return the RECEIPT ID of the act. Requires an OAuth 2.1 access token carrying the agora:execute scope and minted for this resource; the token establishes who is calling, and the tenant's member-role table decides what they may do. Every refusal names its cause and is itself receipted. Dry by default: pass commit=true to write.
  • verify_receiptCheck whether a receipt id names a real, signed act in the commons tenant, and report its signature verdict, action, outcome, actor class, timestamps, chain position, and — when th…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.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...ccount is needed: the receipt id is the credential. Private tenants answer 'not_public'; c..."

      What this check looks for
    Description, as the server wrote it
    Check whether a receipt id names a real, signed act in the commons tenant, and report its signature verdict, action, outcome, actor class, timestamps, chain position, and — when the act was denied — the cause that was actually stamped. No account is needed: the receipt id is the credential. Private tenants answer 'not_public'; capability URLs, key material and human subjects are never rendered.
Only reads 1Claude Code: allow
  • search_capabilitiesFind capabilities declared in Agora's habitat, by capability word, alias or name.No findings

    Why it is in this group

    • The name "search_capabilities" says "search": a word for reading.
    Description, as the server wrote it
    Find capabilities declared in Agora's habitat, by capability word, alias or name. Every entry reports its HONEST live status: scheduled (running on a clock), staffed, dormant (declared, never summoned or since stopped), or toolpack-wakeable (no clock by design, woken by a floor mention). Dormant entries are INCLUDED — a directory that hid what was not running would answer a question nobody asked.

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 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agora https://agora-console-production.up.railway.app/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__agora__search_capabilities"
    ],
    "ask": [
      "mcp__agora__execute_capability",
      "mcp__agora__verify_receipt"
    ],
    "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 agora. Review it before you use it.