protogrid

Search / so.anteroom/anteroom

anteroom

R0· no sign-in

Frontier-AI vendor commitments, safety framework history, corpus, and partnership patterns.

v0.1.0 · active · repository · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality79good
Trust85of 100
Uptime, 30 days92%
Latency p50230 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "anteroom": {
      "type": "http",
      "url": "https://mcp.anteroom.so/mcp"
    }
  }
}
claude mcp add --transport http anteroom https://mcp.anteroom.so/mcp
[mcp_servers.anteroom]
url = "https://mcp.anteroom.so/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "anteroom": {
      "type": "remote",
      "url": "https://mcp.anteroom.so/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "anteroom": {
      "type": "http",
      "url": "https://mcp.anteroom.so/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=anteroom&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLmFudGVyb29tLnNvL21jcCJ9"
}
{
  "servers": {
    "anteroom": {
      "type": "http",
      "url": "https://mcp.anteroom.so/mcp"
    }
  }
}
{
  "mcpServers": {
    "anteroom": {
      "httpUrl": "https://mcp.anteroom.so/mcp"
    }
  }
}
extensions:
  "anteroom":
    enabled: true
    name: "anteroom"
    type: streamable_http
    uri: "https://mcp.anteroom.so/mcp"
    timeout: 300

Quality 79 / 100good

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
  • n/a
    protocol.statelessonly applies to 2026-07-28 servers
  • pass
    protocol.transportstreamable HTTP
  • n/a
    protocol.list_ttlonly applies to 2026-07-28 servers
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene71 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • fail
    tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_partnership_pattern (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_vendor_commitments (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_framework_version_history (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
  • pass
    tools.token_costabout 868 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability100 · weight 15
  • pass
    stability.changesno tool changes in 30 days
  • pass
    stability.rug_pullno tool changed its meaning under the same name
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

5 tools, about 868 tokens to load them all · tool set 40a497186c38 · checked 2026-10-20 12:13 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 85 / 100

provenance75
liveness97
freshness65
hygiene100

+repository +dns-namespace +reachable +uptime-92% ~updated-110d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://mcp.anteroom.so/mcp streamable-httpnoneyes92%230 ms2025-11-252026-10-20

Tools (5)

get_framework_version_historyGet the full version ledger of a frontier AI lab's safety framework (Responsible Scaling Policy, Preparedness Framework, Frontier Safety Framework, or equivalent). Returns every published version, effective date, published changelog, and primary source URL.
get_partnership_patternGet a named strategic AI partnership pattern with its plain-language description, example clauses, kill-list moves, scholarly anchors, and real-world precedent anchors.
get_partnerships_by_patternList every tracked public AI strategic partnership that Anteroom has classified as an instance of a given pattern. Returns partnership metadata with permalink to the primary-source-anchored deal page.
get_vendor_commitmentsGet the seven tracked commercial commitments (AUP, no-train default, output ownership, IP indemnity program, retention default, deprecation notice, safety framework version) for a frontier AI vendor. Each commitment carries the quoted primary-source text, source URL, and effective date.
search_corpusSearch Anteroom's tracked corpus of AI-relevant regulatory provisions across jurisdictions (EU AI Act, US state laws, sectoral rules, international frameworks) and legal lenses. Returns matching provisions with primary-source URLs and confidence tags.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "so.anteroom/anteroom",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-07-09/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.anteroom.so/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.1.0",
  "repository": {
    "url": "https://github.com/marcusharjani/preflight",
    "source": "github",
    "subfolder": "mcp-server"
  },
  "description": "Frontier-AI vendor commitments, safety framework history, corpus, and partnership patterns."
}