tool_recommend

SERVERMcp Knowledge SOURCEhttps://mcp.gapup.io

Low RISK CLASS

Category Read

Parameters 61 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-getgapup-mcp-knowledge/tool-recommend.md

WHAT IT DOES

What tool_recommend does on Mcp Knowledge

AI agents call tool_recommend to retrieve information from Mcp Knowledge without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Parameter	Type	Required	Description
`lang`	string	—	Optional ISO 639-1 language hint (fr, en, de, zh, es …). Used for language-aware boosting.
`async`	boolean	—	If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client ti
`domain`	string	—	Optional domain hint to boost tools in this category.
`intent`	string	Yes	Free-text description of what you want to accomplish. E.g. 'Run a full M&A due diligence on Acme Corp' or 'Je veux vérifier qu'un fournisseur n'est pas sous san
`max_results`	number	—	Max number of recommendations returned (1-10). Default 5.
`include_chain`	boolean	—	Whether to include a suggested_chain of tools in the optimal sequence. Default true. Chain is always included for well-known intents (M&A, compliance, ESG, etc.

Parameters from the server's own tool schema.

RISK

Why tool_recommend is rated Low

This is a discovery and recommendation tool that queries metadata about other tools in the catalogue and returns ranked results with suggestions. It has no side effects—it retrieves information to help users choose tools but does not execute those tools, modify data, or trigger external operations. The tool itself is purely informational (Read category).

From the tool's definition Tool returns recommendations and suggestions without modifying data: 'returns the most appropriate tools', 'ranked by confidence, with pre-filled input suggestions'. The word 'Pure' at the end (likely truncated) reinforces this is a query/navigation function.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs tool_recommend safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Knowledge, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For tool_recommend, this is the rule to start with:

tool_recommend Allowed

tool_recommend is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "tool_recommend": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Knowledge, apply this rule, and every tool_recommend call is checked against it from then on.

FAQ

Questions about tool_recommend

What does the tool_recommend tool do? +

Cross-tool recommendation system: given a free-text intent, returns the most appropriate tools from the 170+ Gapup MCP catalogue, ranked by confidence, with pre-filled input suggestions and an optimal multi-tool chain when applicable. Use this first when you are unsure which tool to call — it navigates the full catalogue for you. Supports 15+ static pre-designed chains for frequent intents (M&A due diligence, sanctions screening, ESG 360, AI Act compliance, FTO patent clearance, crypto wallet tracking, etc.). Domains: compliance | finance | intel | legal | content | data | trade | infra. Pure compute — $0.01/call, no external fetch. Ideal as a first call in any multi-step agent workflow. It is categorised as a Read tool in the Mcp Knowledge MCP Server, which means it retrieves data without modifying state.

What parameters does tool_recommend accept? +

tool_recommend accepts 6 parameters: lang, async, domain, intent, max_results, include_chain. Required: intent. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on tool_recommend? +

Register the Mcp Knowledge MCP server in PolicyLayer and add a rule for tool_recommend: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Knowledge. Nothing to install.

What risk level is tool_recommend? +

tool_recommend is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit tool_recommend? +

Yes. Add a rate_limit block to the tool_recommend rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block tool_recommend completely? +

Set action: deny in the PolicyLayer policy for tool_recommend. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides tool_recommend? +

tool_recommend is provided by the Mcp Knowledge MCP server (https://mcp.gapup.io). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Mcp Knowledge, and thousands of servers like it.

This server

All 271 Mcp Knowledge tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →