// SCAN REPORT

WeKnora MCP Server

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

4 destructive tools with no built-in limits. Policy required.

Last updated: 12 Jun 2026

10 can modify or destroy data

11 read-only

21 tools total

Community server · catalogue entry verified 12/06/2026

How to control WeKnora MCP Server ↓

TOOL MAP

What WeKnora MCP Server exposes to your agents

Read (11) Write / Execute (6) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous WeKnora MCP Server tools

Destructive · High delete_chunk Deleting a chunk is a destructive action that cannot be undone—it permanently removes a unit of knowledge from the knowledge base. Destructive · High delete_knowledge This tool permanently removes knowledge entries from the WeKnora knowledge management system. Destructive · High delete_knowledge_base Deleting a knowledge base is an irreversible operation that removes an entire collection of data. Destructive · High delete_session The tool performs a delete operation on session objects, which is irreversible and destroys data.

10 of WeKnora MCP Server's 21 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control WeKnora MCP Server

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

Deny destructive operations

{
  "delete_chunk": {
    "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

{
  "create_knowledge_base": {
    "limits": [
      {
        "counter": "create_knowledge_base_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_knowledge": {
    "limits": [
      {
        "counter": "get_knowledge_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 WeKnora MCP Server — 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 WEKNORA →

Free to start. No card required.

FULL CATALOGUE

All 21 WeKnora MCP Server tools

DESTRUCTIVE 4 tools

Destructive delete_chunk Delete a chunk Destructive delete_knowledge Delete knowledge Destructive delete_knowledge_base Delete a knowledge base Destructive delete_session Delete a session

EXECUTE 1 tools

Execute chat Send a chat message to a session

WRITE 5 tools

Write create_knowledge_base Create a new knowledge base Write create_knowledge_from_url Create knowledge from URL Write create_model Create a new model Write create_session Create a new chat session Write create_tenant Create a new tenant in WeKnora

READ 11 tools

Read get_knowledge Get knowledge details Read get_knowledge_base Get knowledge base details Read get_model Get model details Read get_session Get session details Read hybrid_search Perform hybrid search in knowledge base Read list_chunks List chunks of knowledge Read list_knowledge List knowledge in a knowledge base Read list_knowledge_bases List all knowledge bases Read list_models List all models Read list_sessions List chat sessions Read list_tenants List all tenants

EXPLORE

Related servers

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

FAQ

Questions about WeKnora MCP Server

Can an AI agent delete data through the WeKnora MCP Server MCP server? +

Yes. The WeKnora MCP Server server exposes 4 destructive tools including delete_chunk, delete_knowledge, delete_knowledge_base. 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 WeKnora MCP Server? +

The WeKnora MCP Server server has 5 write tools including create_knowledge_base, create_knowledge_from_url, create_model. 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 WeKnora MCP Server.

How many tools does the WeKnora MCP Server MCP server expose? +

21 tools across 3 categories: Destructive, Read, Write. 11 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on WeKnora MCP Server? +

Register the WeKnora MCP Server 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 WeKnora MCP Server tool call.

Deterministic rules across all 21 WeKnora MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON WEKNORA →

Free to start. No card required.

21 WeKnora MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.