Anteroom MCP server

• Registry nameso.anteroom/anteroomverified in the MCP registry

The registry name sits under anteroom.so. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-26
• Tools5
• Server calls itselfanteroom
• Server version0.1.0
• Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 146 ms.

• Its tools do every use case we checked: Identify regulations that apply before shipping an AI feature; Review obligations and dealbreakers for an AI partnership.
• Checked on 2 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
• What an agent can do with it2 of 2 use cases
• Answeredmeasuring2 of the 7 daily checks it takes to print a share
• Median first answer159 ms
• Space in an agent's context≈ 920 tokensthe definitions of all its tools (5), which an agent carries on every turn
• Tool definitionsB · 83 of 100
• Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once

• Not saying whether it only reads or can destroy: 5 of 5

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• get_vendor_commitments

  Get 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…

• get_framework_version_history

  Get 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…

• search_corpus

  Search 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…

• get_partnership_pattern

  Get 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_pattern

  List 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.