Maple

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

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

Last updated:

10 can modify or destroy data
19 read-only
29 tools total

Community server · catalogue entry verified 03/07/2026

How to control Maple ↓

What Maple exposes to your agents

Read (19) Write / Execute (10) Destructive / Financial (0)
High Risk

The most dangerous Maple tools

10 of Maple's 29 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Maple

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

Rate limit write operations
{
  "ingest_session_event": {
    "limits": [
      {
        "counter": "ingest_session_event_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "arxiv_search": {
    "limits": [
      {
        "counter": "arxiv_search_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register Maple — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON MAPLE →

Instant setup, no code required.

All 29 Maple tools

READ 19 tools
Read arxiv_search Search arXiv papers and return titles, authors, abstracts, and links. Read audit_risk Audit a trace for anomalies and risky behavior (shell/network/credentials) and return a risk dashboard. Read export_trace Export a trace in JSON or Markdown format for sharing and debugging. Read github_repo_info Get public metadata and health signals for a GitHub repository. Read hn_search Search Hacker News stories/comments with ranking metadata. Read list_downstream_apps List downstream MCP apps registered behind Maple. Clients should call Maple only and dispatch via this control Read list_downstream_tools List tools exposed by a registered downstream MCP app through Maple proxy routing. Read list_traces List recent traces and risk metadata. Read maple_get_started LLM quickstart for Maple routing. Returns the exact next MCP calls (search/connect/call) based on current Mapl Read maple_marketplace_connected_apps List currently connected marketplace apps registered in Maple. Read maple_marketplace_search Search MCP marketplaces (Smithery and MCP.so) and return connectable servers Maple can route through firewall Read observe_session Start observing an agent session, store its execution trace, and render a live timeline widget. Read openlibrary_search Search OpenLibrary for books with authors, year, and canonical URLs. Read suggest_evolved_skills Generate evolved skill suggestions from anonymized shared traces using embedding similarity. Read weather_forecast Get a short multi-day weather forecast for a location using Open-Meteo. Read web_fetch Fetch and extract readable content from a public web page URL. Read web_search Search the public web for a query and return ranked snippets with URLs. Read wikipedia_summary Get a concise summary for a Wikipedia topic title. Read yc_app_brief Generate YC-ready positioning with moat, traction, and freemium revenue narrative using live product metrics.

Related servers

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

Questions about Maple

How do I prevent bulk modifications through Maple? +

The Maple server has 5 write tools including ingest_session_event, maple_marketplace_connect, maple_marketplace_disconnect. 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 Maple.

How many tools does the Maple MCP server expose? +

29 tools across 3 categories: Execute, Read, Write. 19 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Maple? +

Register the Maple 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 Maple tool call.

Deterministic rules across all 29 Maple tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

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

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.