// SCAN REPORT

Mnemos

15 tools. 7 can modify or destroy data without limits.

7 write tools that can modify data. Rate limits recommended.

Last updated: 11 Jun 2026

7 can modify or destroy data

8 read-only

15 tools total

Community server · catalogue entry verified 11/06/2026

How to control Mnemos ↓

TOOL MAP

What Mnemos exposes to your agents

Read (8) Write / Execute (7) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Mnemos tools

Execute · Medium hive.message_publish Publishing a message triggers an external operation (message delivery, potentially to multiple recipients via broadcast) whose effects depend on the arguments (recipient URN, message content). Execute · High graeae.consult This tool triggers external LLM operations (potentially multiple, in debate or all modes), routing requests to one or more language models. Write · Medium hive.agent_register This tool creates a new record (agent registration) in the Hive system, which is a reversible modification. Write · Medium hive.job_create The tool creates and submits new work items (jobs) into a queue, which is a write operation.

7 of Mnemos's 15 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mnemos

PolicyLayer is an MCP gateway — it sits between your AI agents and Mnemos, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "hive.job_next": {
    "limits": [
      {
        "counter": "hive.job_next_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "graeae.get": {
    "limits": [
      {
        "counter": "graeae.get_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Mnemos — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MNEMOS →

Free to start. No card required.

FULL CATALOGUE

All 15 Mnemos tools

EXECUTE 2 tools

Execute graeae.consult Submit a multi-LLM consensus consultation to GRAEAE (PYTHIA). Modes: auto/single/all/debate/majority. Execute hive.message_publish Publish a Hive message. to_urn=null for broadcast.

WRITE 5 tools

Write hive.job_next Atomic dequeue: claim highest-priority eligible job for this agent. Returns job or {204: no work}. Write hive.agent_register Register this session as an agent in the Hive. Returns urn + session_id. Write hive.job_create Submit work into the Hive Mind triage queue. Eligible agents self-claim. Write hive.job_update Update job status/result. Status: queued/claimed/running/done/failed/cancelled. Write mnemos.memory_create Save a memory to MNEMOS. Category: infrastructure/solutions/patterns/decisions/projects/standards.

READ 8 tools

Read graeae.get Get a previous GRAEAE consultation by id. Read graeae.modes List GRAEAE consultation modes + their descriptions. Read graeae.muses List available GRAEAE muses (LLM providers + models). Read hive.agent_list List registered agents in the GRAEAE Hive Mind. Read hive.job_list List jobs in the Hive. Filter by status/agent/since. Read hive.message_list List Hive messages. Filter by recipient/topic. Read mnemos.memory_get Get a MNEMOS memory by id (mem_XXX). Read mnemos.memory_search Search MNEMOS memory (PYTHIA). Semantic+keyword.

FAQ

Questions about Mnemos

How do I prevent bulk modifications through Mnemos? +

The Mnemos server has 5 write tools including hive.job_next, hive.agent_register, hive.job_create. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Mnemos.

How many tools does the Mnemos MCP server expose? +

15 tools across 2 categories: Read, Write. 8 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Mnemos? +

Register the Mnemos MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Mnemos tool call.

Deterministic rules across all 15 Mnemos tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MNEMOS →

Free to start. No card required.

15 Mnemos tools catalogued and risk-classified — across an index of 43,000+ MCP servers.