A
licenseNot graded
qualityC
maintenanceEnforces fine-grained, context-aware access control on MCP tool calls, with a tamper-evident, replayable audit log that records denials and verifies every decision.
MIT
Enforcer
Server Details
Identity and authorization in one system: allow, deny, the reason, and a record.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP
- URL
- ChatGPT
- –
- Claude
- –
TDQS
A4.4/5.0
Scored across 7 tools
Disambiguation5/5
Each tool has a clearly distinct role: auth config discovery, SIWE nonce issuance, login, token refresh, registration, and OTP request by channel. The only adjacent pair, requestOtp and requestSms, is cleanly separated by email versus phone.
Naming Consistency4/5
Most tools follow a verb_noun camelCase pattern like getAuthConfig, getSiweNonce, requestOtp, and refreshToken. The bare verbs login and register are minor deviations but are conventional auth actions, so the set remains predictable.
Tool Count5/5
Seven tools is well-scoped for an authentication-focused server. Each tool addresses a necessary step in the auth lifecycle without redundancy or filler.
Completeness4/5
The toolset covers configuration discovery, SIWE and OTP authentication, registration, login, and token refresh. The main gap is the lack of an explicit logout or token revocation tool, though agents can discard tokens and the refresh token reuse behavior provides some reclamation.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Deterministic allow/require_approval/deny verdicts for agent actions, before they happen.
Authorize AI agent tool calls before they run: policy-as-code, human approval, signed receipts.
Ask a sealed authority whether an action may proceed. Answers are deterministic and citable.
Owner-signed permissions for AI agent actions; ALLOW/BLOCK/REVIEW with request-bound receipts.
Related MCP Servers
- AlicenseAqualityDmaintenanceDefault-deny action registry, append-only spend ledger, and human sign-off audit trail (MCP tools).6MIT
- AlicenseNot gradedqualityDmaintenanceEnforces identity-based access control and audit logging for MCP servers, letting you grant fine-grained tool permissions to users and systems while failing secure by default.MIT
- AlicenseAqualityBmaintenanceEnables AI agents to obtain signed permit, deny, or escalation decisions before destructive, deployment, or spending actions, then commit actual effects to a hash-chained, signed audit log.461 npmApache 2.0
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd
Glama MCP Gateway
Add one secure layer between your agents and this server.