ACR — AGENT COMPOSITION RECORDS TOOLS

30 tools from the ACR — Agent Composition Records MCP Server, categorised by risk level.

READ 22 tools
Read check_entity Ask the ACR network what it knows about a specific skill hash, agent, or system. Returns the raw behavioral... Read check_environment Check the current ACR network environment: pipeline health (status, aggregation freshness, known issues) an... Read dismiss_pattern Dismiss a proactive pattern surfaced on get_my_agent or whats_new. The pattern won't appear again even if t... Read get_compensation_signatures Query the compensation-signatures lens: how stereotyped is your chain-shape behavior, and which chain patte... Read get_composition_diff Compare your declared composition (MCPs, APIs, skills from register_agent / update_composition) against the... Read get_coverage Signal coverage: which fields you populate on your receipts and which you don't. Shows transparent rules wi... Read get_failure_registry Failure registry: per-target breakdown of failures — status codes, error codes, categories, and median dura... Read get_friction_report Query the friction lens of your interaction profile — one of several lenses available (more on the roadmap)... Read get_interaction_log View your interaction history. Use mode "list" for a scannable log, or "detail" (or provide receipt_id) for... Read get_my_agent Identity card for your ACR agent: agent ID, API key, dashboard link, provider class, status. Pure identity ... Read get_network_status Network-wide observation dashboard. Shows agent and system totals, system signal rates sorted worst-first, ... Read get_notifications An anomaly signal is a behavioral pattern ACR observed across multiple unrelated agents (not a security eve... Read get_profile Your interaction profile: identity, composition summary, composition delta (MCP-observed vs agent-reported)... Read get_revealed_preference Query the revealed-preference lens: what the agent *declared* in its composition vs what it *actually calle... Read get_skill_tracker Track skill adoption and anomaly signal rates across the agent population. Use without skill_hash for an ov... Read get_skill_versions Get version history for a skill. Shows how it has changed over time, whether your version is current, and h... Read get_stable_corridors Stable corridors: interaction paths that are consistently reliable — zero failures, low latency variance, s... Read get_tier_features Show what each ACR tier (free, paid) includes — full feature comparison. Use this when you want to know wha... Read get_trend Trend: per-target latency and failure rate changes over time. Compares current period to previous period an... Read list_watches List your registered watches — (lens, target, metric, threshold, condition) plus when each was last evaluat... Read search_skills Search ACR network knowledge about a skill by name, description, or capability. Returns raw signals observe... Read summarize_my_agent [DEPRECATED — call `orient_me` instead.] One-call snapshot of profile, friction, and coverage. Superseded b...

The managed route: connect ACR — Agent Composition Records through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @tethral/acr-mcp
How many tools does the ACR — Agent Composition Records MCP server have? +

The ACR — Agent Composition Records MCP server exposes 30 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on ACR — Agent Composition Records tools? +

Route the ACR — Agent Composition Records server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do ACR — Agent Composition Records tools fall into? +

ACR — Agent Composition Records tools are categorised as Read (22), Write (5), Destructive (1), Execute (2). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.