// SCAN REPORT

Knowledgelib

6 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 3 Jul 2026

1 can modify or destroy data

5 read-only

6 tools total

Community server · catalogue entry verified 03/07/2026

How to control Knowledgelib ↓

TOOL MAP

What Knowledgelib exposes to your agents

Read (5) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Knowledgelib tools

Write · Low report_issue report_issue creates new data (issue reports) in a knowledge base feedback system.

1 of Knowledgelib's 6 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Knowledgelib

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

Rate limit write operations

{
  "report_issue": {
    "limits": [
      {
        "counter": "report_issue_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "batch_query": {
    "limits": [
      {
        "counter": "batch_query_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 Knowledgelib — 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 KNOWLEDGELIB →

Instant setup, no code required.

FULL CATALOGUE

All 6 Knowledgelib tools

WRITE 1 tools

Write report_issue Flag incorrect, outdated, or broken content on a knowledge unit. Reports are reviewed and used to prioritize c

READ 5 tools

Read batch_query Search multiple topics in a single call. More efficient than calling query_knowledge multiple times. Max 10 qu Read get_unit Retrieve a specific knowledge unit by ID. Returns the full raw markdown with YAML frontmatter, inline source c Read list_domains List all available knowledge domains with unit counts. Use this to discover what topics are covered before que Read query_knowledge STEP 1: Search across all knowledgelib.io knowledge units. Returns matching units ranked by relevance with met Read suggest_question STEP 3: Submit a question or topic request. ALWAYS call this when query_knowledge returned no results. Popular

FAQ

Questions about Knowledgelib

How do I prevent bulk modifications through Knowledgelib? +

The Knowledgelib server has 1 write tools including report_issue. 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 Knowledgelib.

How many tools does the Knowledgelib MCP server expose? +

6 tools across 2 categories: Read, Write. 5 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Knowledgelib? +

Register the Knowledgelib 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 Knowledgelib tool call.

Deterministic rules across all 6 Knowledgelib tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON KNOWLEDGELIB →

Instant setup, no code required.

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