// SCAN REPORT

Archmind

4 tools. 3 can modify or destroy data without limits.

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

Last updated: 11 Jun 2026

3 can modify or destroy data

1 read-only

4 tools total

Community server · catalogue entry verified 06/05/2026 · full schemas captured for 4 of 4 tools

How to control Archmind ↓

TOOL MAP

What Archmind exposes to your agents

Read (1) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Archmind costs in tokens

309 tokens of tool definitions, loaded on every request

0.2% of a 200k context window

97 heaviest tool: generate_architecture

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Archmind tools

Execute · Medium render_mermaid Rendering code (even diagram code) involves executing a processing pipeline that interprets and runs the Mermaid.js DSL to produce a PNG artifact. Write · Medium save_diagram This tool creates and writes file artifacts (PNG images) to the local filesystem. Write · Low generate_architecture This tool creates a new artifact (a diagram in Mermaid.js format) based on user input.

3 of Archmind's 4 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Archmind

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

Rate limit write operations

{
  "generate_architecture": {
    "limits": [
      {
        "counter": "generate_architecture_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_repo": {
    "limits": [
      {
        "counter": "analyze_repo_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 Archmind — 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 ARCHMIND →

Free to start. No card required.

FULL CATALOGUE

All 4 Archmind tools

EXECUTE 1 tools

Execute render_mermaid Renders Mermaid.js code as a PNG image.

WRITE 2 tools

Write generate_architecture Generates a technical architecture diagram in Mermaid.js format from a natural language prompt. Write save_diagram Renders Mermaid.js code as a PNG image and saves it to a local file.

READ 1 tools

Read analyze_repo Analyzes a GitHub repository and returns a structured summary used for architecture generation.

FAQ

Questions about Archmind

How do I prevent bulk modifications through Archmind? +

The Archmind server has 2 write tools including generate_architecture, save_diagram. 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 Archmind.

How many tools does the Archmind MCP server expose? +

4 tools across 2 categories: Read, Write. 1 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Archmind? +

Register the Archmind 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 Archmind tool call.

Deterministic rules across all 4 Archmind tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ARCHMIND →

Free to start. No card required.

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