// SCAN REPORT

Mnemosyne MCP

57 tools. 28 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 29 Jun 2026

28 can modify or destroy data

29 read-only

57 tools total

Community server · catalogue entry verified 29/06/2026

How to control Mnemosyne MCP ↓

TOOL MAP

What Mnemosyne MCP exposes to your agents

Read (29) Write / Execute (23) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Mnemosyne MCP tools

Destructive · Medium cancel_job Cancelling a queued job is an irreversible action - once cancelled, the job's execution is terminated and cannot be undone. Destructive · High delete The 'delete' tool operates in the Mnemosyne knowledge graph system where data is stored persistently in RDF graphs. Destructive · High manage_graph While the tool also supports non-destructive operations (read metadata, get stats), the most severe capability available is 'delete graph', which would irreversibly destroy an entire knowledge graph and all its contents. Execute · High sparql_update SPARQL UPDATE can perform INSERT, DELETE, DROP, and CLEAR operations on RDF graphs.

28 of Mnemosyne MCP's 57 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mnemosyne MCP

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

Deny destructive operations

{
  "cancel_job": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "archive_memories": {
    "limits": [
      {
        "counter": "archive_memories_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_document": {
    "limits": [
      {
        "counter": "check_document_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 Mnemosyne MCP — 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 MNEMOSYNE →

Instant setup, no code required.

FULL CATALOGUE

All 57 Mnemosyne MCP tools

DESTRUCTIVE 3 tools

Destructive cancel_job Cancel a queued job. Only jobs that haven Destructive delete delete Destructive manage_graph Manage knowledge graph: read metadata, get stats, or delete graph

EXECUTE 5 tools

Execute query_graph Execute SPARQL query on knowledge graph, return filtered results (max 100 rows) Execute reindex_graph reindex_graph Execute sparql_query sparql_query Execute sparql_update sparql_update Execute update_graph Execute SPARQL update (INSERT/DELETE) on knowledge graph

WRITE 18 tools

Write archive_memories archive_memories Write create_folder create_folder Write create_graph Create new knowledge graph with title and optional description Write create_wires create_wires Write duplicate_graph duplicate_graph Write edit_block_text edit_block_text Write edit_comment edit_comment Write ingest_artifact ingest_artifact Write insert_blocks insert_blocks Write make_document_editable make_document_editable Write move_documents move_documents Write move_folder move_folder Write rename rename Write set_home_graph Set or clear the session's default graph. Write store_memory store_memory Write update_blocks update_blocks Write upload_artifact upload_artifact Write write_document write_document

READ 29 tools

Read check_document check_document Read context_bundle context_bundle Read document_digest document_digest Read dump_chat dump_chat Read get_block get_block Read get_block_values get_block_values Read get_document_history get_document_history Read get_important_blocks get_important_blocks Read get_session_state get_session_state Read get_user_location Get the user's current graph and document IDs. Read get_values get_values Read get_wires get_wires Read get_workspace get_workspace Read list_graphs List graphs owned by the authenticated user. Read list_wire_predicates list_wire_predicates Read music music Read query_blocks query_blocks Read quick_orient quick_orient Read read_blocks read_blocks Read read_document read_document Read read_document_at_snapshot read_document_at_snapshot Read recall recall Read remember remember Read revaluate revaluate Read search_blocks search_blocks Read search_documents search_documents Read surface surface Read traverse_wires traverse_wires Read value value

OTHER 2 tools

Other care care Other sing sing

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Mnemosyne MCP

Can an AI agent delete data through the Mnemosyne MCP server? +

Yes. The Mnemosyne MCP server exposes 3 destructive tools including cancel_job, delete, manage_graph. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Mnemosyne MCP? +

The Mnemosyne MCP server has 18 write tools including archive_memories, create_folder, create_graph. 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 Mnemosyne MCP.

How many tools does the Mnemosyne MCP server expose? +

57 tools across 3 categories: Destructive, Read, Write. 29 are read-only. 28 can modify, create, or delete data.

How do I enforce a policy on Mnemosyne MCP? +

Register the Mnemosyne 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 Mnemosyne MCP tool call.

Deterministic rules across all 57 Mnemosyne MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MNEMOSYNE →

Instant setup, no code required.

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