// SCAN REPORT

Open MCP Knowledgebase

11 tools. 2 can modify or destroy data without limits.

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

Last updated: 2 Jul 2026

2 can modify or destroy data

9 read-only

11 tools total

Community server · catalogue entry verified 02/07/2026

How to control Open MCP Knowledgebase ↓

TOOL MAP

What Open MCP Knowledgebase exposes to your agents

Read (9) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Open MCP Knowledgebase tools

Execute · Medium twelvelabs_analyze This tool executes an external API operation against a third-party video intelligence service (TwelveLabs), making it Execute rather than Read. Write · Low write_content The tool creates or modifies text content in a reversible, non-persistent manner.

2 of Open MCP Knowledgebase's 11 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Open MCP Knowledgebase

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

Rate limit write operations

{
  "write_content": {
    "limits": [
      {
        "counter": "write_content_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_document": {
    "limits": [
      {
        "counter": "get_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 Open MCP Knowledgebase — 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 OPEN MCP KNOWLEDGEBASE →

Instant setup, no code required.

FULL CATALOGUE

All 11 Open MCP Knowledgebase tools

EXECUTE 1 tools

Execute twelvelabs_analyze Analyze a specific video using the TwelveLabs integration bound to a content scope. Call list_integrations fir

WRITE 1 tools

Write write_content Write, rewrite, condense, or polish content through a configured AI Gateway model. Use this for final prose a

READ 9 tools

Read get_document Read one source from the ${surface.label} surface. Omit topic to get the overview plus topic table of contents Read get_skill Fetch exactly one skill by id after list_skills identifies a relevant match. Inline skills return their full i Read list_integrations Call this before any provider-backed tool. It resolves the requested content scope to configured provider inte Read list_skills Call this before get_skill to choose the right skill for the task. Match each row Read mixedbread_agentic_search Run multi-round, LLM-driven Mixedbread retrieval against the store bound to a content scope. Use when one sema Read mixedbread_answer Ask a cited-answer question against the Mixedbread store bound to a content scope. Use when a written answer w Read mixedbread_search Single-pass semantic search against the Mixedbread store bound to a content scope. Call list_integrations firs Read search_documents Search the ${surface.label} surface when the exact topic is unknown. For large corpora, call list_sources firs Read twelvelabs_search Search the TwelveLabs video index bound to a content scope. Call list_integrations first, then pass only scope

FAQ

Questions about Open MCP Knowledgebase

How do I prevent bulk modifications through Open MCP Knowledgebase? +

The Open MCP Knowledgebase server has 1 write tools including write_content. 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 Open MCP Knowledgebase.

How many tools does the Open MCP Knowledgebase MCP server expose? +

11 tools across 2 categories: Read, Write. 9 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Open MCP Knowledgebase? +

Register the Open MCP Knowledgebase 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 Open MCP Knowledgebase tool call.

Deterministic rules across all 11 Open MCP Knowledgebase tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON OPEN MCP KNOWLEDGEBASE →

Instant setup, no code required.

11 Open MCP Knowledgebase tools catalogued and risk-classified — across an index of 43,000+ MCP servers.