peopleSearch_tool

// WHEN AI AGENTS USE THIS TOOL

AI agents call peopleSearch_tool to retrieve information from Fiber without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

// WHY ENFORCE A POLICY ON PEOPLESEARCH_TOOL

Even though peopleSearch_tool only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

// RECOMMENDED POLICY

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

fiberai-fiber-mcp.yaml

tools:
  peopleSearch_tool:
    rules:
      - action: allow

See the full Fiber policy for all 10 tools.

// DETAILS

Tool Name peopleSearch_tool

Category Read

MCP Server Fiber MCP Server

Risk Level Low

// MORE FIBER TOOLS

Execute syncContactEnrichment_tool Read companyLiveEnrich_tool Read companySearch_tool Read getCompanyExclusionLists_tool Read getOrgCredits_tool Read pollBatchContactEnrichment_tool Read pollCombinedSearch_tool Read pollContactEnrichmentResult_tool

View all 10 tools →

// WHAT CAN GO WRONG

Agents calling read-class tools like peopleSearch_tool have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER READ TOOLS ACROSS MCP SERVERS

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

Open Library MCP Server get_author_info Open Library MCP Server get_author_photo Open Library MCP Server get_authors_by_name Open Library MCP Server get_book_by_id Open Library MCP Server get_book_by_title Open Library MCP Server get_book_cover

// RELATED READING

// FAQ

What does the peopleSearch_tool tool do? +

People search. USE THIS WHEN: - Search for people/profiles DO NOT USE FOR: - Getting email/phone directly (use syncContactEnrichment after finding profile) - Company searches (use companySearch) EXAMPLE: Input: peopleSearch_tool(apiKey="sk_live_...", searchParams={}, pageSize=123) INPUT SCHEMA: Required parameters: - apiKey (string): Your Fiber API key. Must start with 'sk_live_' or 'sk_test_'. Example: 'sk_live_dR6DxD3HT7oJqTEV' Optional parameters: - searchParams (object): Search parameters for people search. - country3LetterCode (['object', 'null']) - numConnections (['object', 'null']) - numFollowers (['object', 'null']) - approxAge (['object', 'null']) - keywords (['object', 'null']) - keywordSearchOptions (['object', 'null']) - jobTitleV2 (['object', 'null']) - exactProfile (['object', 'null']) - startedInRole (any) - startedAtCompany (any) - location (['object', 'null']) - pastJobs (['object', 'null']) - languages (['object', 'null']) - leftStealthAt (any) - isInStealth (['boolean', 'null']) - stealthV2 (any) - jobStatus (any) - timeZone (['object', 'null']) - pastJobText (['object', 'null']) - fuzzyName (['object', 'null']) - companyMatchMode (any) - yearsOfExperience (['object', 'null']) - jobTitleV3 (['object', 'null']) - hasProfilePicture (['boolean', 'null']) - state (['object', 'null']) - getDetailedEducation (['boolean', 'null']) - getDetailedWorkExperience (['boolean', 'null']) - tags (['object', 'null']) - education (['object', 'null']) - pageSize (integer): The number of profiles to return, if you need to get more results, you can paginate. - cursor (['string', 'null']): A pagination cursor returned from a previous search response. Use this to fetch the next page of results. - currentCompanies (['array', 'null']): Filter people by the companies they are currently working for. If you want to search over many companies, we suggest using the Combined Search API, which is optimized for this use case. - prospectExclusionListIDs (['array', 'null']): Filter out people which belong to the given prospect exclusion lists - companyExclusionListIDs (['array', 'null']): Filter out people who work at companies which belong to the given company exclusion lists RETURNS: Response object with keys: output, chargeInfo, warnings PERFORMANCE HINT: - Set pageSize=1 to avoid overwhelming the LLM with too much data. - Only request more if specifically asked by the user. COMMON MISTAKES: - Missing apiKey in function call (apiKey is required) - Invalid API key format (must be 18-50 characters) - API key not in request body (always pass as parameter). It is categorised as a Read tool in the Fiber MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on peopleSearch_tool? +

Add a rule in your Intercept YAML policy under the tools section for peopleSearch_tool. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Fiber MCP server.

What risk level is peopleSearch_tool? +

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

Can I rate-limit peopleSearch_tool? +

Yes. Add a rate_limit block to the peopleSearch_tool rule in your Intercept 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 peopleSearch_tool completely? +

Set action: deny in the Intercept policy for peopleSearch_tool. 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 peopleSearch_tool? +

peopleSearch_tool is provided by the Fiber MCP server (fiberai/fiber-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Fiber