openaudit-site
Registry code: cba3e9fe9c2888fb
Read-only reference for openaudit, served from the openaudit.se website: look up auditors and their playbooks, search the docs, read the config schema and get install instructions. This server cannot run audits. To audit a codebase, URL, container or app, install the full local MCP server, which runs audits on the user's machine: `claude mcp add openaudit -- bunx @openaudit/cli mcp` (get_install_instructions has the setup for other clients).
- endpoint
- https://openaudit.se/mcp
- protocol
- streamable-http ·2025-06-18
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is openaudit-site live?
- Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
- Is openaudit-site free to use?
- Yes — the hub reached it with no key and no payment.
- What tools does openaudit-site have?
- 5 tools: get_auditor, search_docs, get_config_schema, list_auditors, get_install_instructions.
- Is openaudit-site safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 100%· all time 100%
last good check
of 5 tools
- unknown → live
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
get_config_schema open 1h ago
The JSON Schema of openaudit.config.json (published at https://openaudit.se/schema/config.json): suppressions, auditor selection and per-auditor settings. Read-only data from openaudit.se; to run audits, use the local server (`bunx @openaudit/cli mcp`).
{ "type": "object", "properties": {}, "additionalProperties": false }arguments 5 lineslist_auditors open 1h ago
List openaudit's auditors, optionally filtered by area, target kind, engine or text. Returns each auditor's id, title, areas, targets and whether it runs by default. Read-only data from openaudit.se; to run audits, use the local server (`bunx @openaudit/cli mcp`).
{ "type": "object", "properties": { "limit": { "type": "integer", "maximum": 200, "minimum": 1, "description": "Most auditors to return (default 50)" }, "query": { "type": "string", "maxLength": 200, "description": "Words that must all appear in the id, title, tool or description" }, "engine": { "type": "string", "maxLength": 40, "description": "builtin, external (wraps a scanner) or agentic" }, "target": { "type": "string", "maxLength": 40, "description": "Target kind: codebase, url, webapp, container, iac, mobile or cloud" }, "category": { "type": "string", "maxLength": 40, "description": "Area, e.g. security, accessibility, performance, seo, privacy, supply-chain" } }, "additionalProperties": false }arguments 32 linesget_install_instructions open 1h ago
How to install and run openaudit: the CLI, the local MCP server for Claude Code, Cursor, VS Code and Codex, MCP over HTTP, the GitHub Action, Docker, GitLab CI, pre-commit and the agent skill. Without a method, lists them all. Read-only data from openaudit.se; to run audits, use the local server (`bunx @openaudit/cli mcp`).
{ "type": "object", "properties": { "method": { "type": "string", "maxLength": 40, "description": "cli, mcp, mcp-http, github-action, docker, gitlab-ci, pre-commit or skill" } }, "additionalProperties": false }arguments 11 linesget_auditor unknown never probed
One auditor by id (e.g. code.secrets, web.headers, agent.authz): what it checks, its targets and areas, the command that runs only it, and its full playbook when it is an agentic auditor. Read-only data from openaudit.se; to run audits, use the local server (`bunx @openaudit/cli mcp`).
{ "type": "object", "required": [ "id" ], "properties": { "id": { "type": "string", "pattern": "^[a-z0-9][a-z0-9._-]*$", "maxLength": 100, "minLength": 1, "description": "Auditor id, as returned by list_auditors" } }, "additionalProperties": false }arguments 16 linessearch_docs unknown never probed
Full-text search over the openaudit docs (CLI, configuration, CI, MCP and agents, HTTP API, report and scoring, safety, contributing). Returns matching sections with a snippet and a link. Read-only data from openaudit.se; to run audits, use the local server (`bunx @openaudit/cli mcp`).
{ "type": "object", "required": [ "query" ], "properties": { "limit": { "type": "integer", "maximum": 10, "minimum": 1, "description": "Most sections to return (default 5, at most 10)" }, "query": { "type": "string", "maxLength": 200, "minLength": 2, "description": "Words to look for, e.g. 'baseline suppressions'" } }, "additionalProperties": false }arguments 21 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's idcba3e9fe9c2888fb.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/cba3e9fe9c2888fb/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/cba3e9fe9c2888fb?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.