// SCAN REPORT

Pg Mnemosyne

12 tools. 10 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 3 Jul 2026

10 can modify or destroy data

2 read-only

12 tools total

Community server · catalogue entry verified 03/07/2026

How to control Pg Mnemosyne ↓

TOOL MAP

What Pg Mnemosyne exposes to your agents

Read (2) Write / Execute (9) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Pg Mnemosyne tools

Destructive · High delete_record This tool permanently removes data from the database without the possibility of automatic recovery (unless backups exist outside this tool's scope). Execute · Critical run_sql Although this tool *could* be used destructively (DELETE/DROP) or for reads (SELECT), its primary risk is that it executes code (SQL) whose effects are entirely argument-dependent. Write · Medium add_column Adding a column to a table modifies the database schema in a reversible manner—columns can be dropped or altered later. Write · Medium add_record The tool creates new records in a database without irreversibly destroying data.

10 of Pg Mnemosyne's 12 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Pg Mnemosyne

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

Deny destructive operations

{
  "delete_record": {
    "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

{
  "add_column": {
    "limits": [
      {
        "counter": "add_column_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_active_sessions": {
    "limits": [
      {
        "counter": "get_active_sessions_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 Pg Mnemosyne — 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 PG MNEMOSYNE →

Instant setup, no code required.

FULL CATALOGUE

All 12 Pg Mnemosyne tools

DESTRUCTIVE 1 tools

Destructive delete_record Deletes a record from the database by its ID.

EXECUTE 1 tools

Execute run_sql Executes arbitrary SQL queries and returns results as JSON.

WRITE 8 tools

Write add_column Adds a new column to a table dynamically. Write add_record Adds a new memory/task record. Write create_project_db Creates a new PostgreSQL database for a project. Write init_coordination_schema Initializes the 'agent_sessions' table for multi-agent coordination. Write init_schema Initializes the base 'records' table in the specified database. Write init_todo_schema Initializes a professional 'tasks' table in the specified database. Write update_agent_session Updates or registers the active task and state of an agent in the database (thread-safe upsert). Write update_record Updates a record in the database by its ID. Only non-None fields will be updated.

READ 2 tools

Read get_active_sessions Retrieves all registered agent coordination sessions ordered by last active time. Read get_records Retrieves recent records from the database.

EXPLORE

Related servers

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

FAQ

Questions about Pg Mnemosyne

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

Yes. The Pg Mnemosyne server exposes 1 destructive tools including delete_record. 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 Pg Mnemosyne? +

The Pg Mnemosyne server has 8 write tools including add_column, add_record, create_project_db. 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 Pg Mnemosyne.

How many tools does the Pg Mnemosyne MCP server expose? +

12 tools across 4 categories: Destructive, Execute, Read, Write. 2 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Pg Mnemosyne? +

Register the Pg 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 Pg Mnemosyne tool call.

Deterministic rules across all 12 Pg Mnemosyne tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PG MNEMOSYNE →

Instant setup, no code required.

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