MCP App Store
by KeenEthics
Sixtyfour Intelligence icon

Sixtyfour Intelligence MCP Server for ChatGPT

By SixtyFourAI

Overview

Deploy AI agents that investigate people and companies, resolve identities, map relationships, and surface risk signals — all through a single API.

How to connect

  1. ChatGPT: Open the Sixtyfour Intelligence listing in the ChatGPT app directory and choose Connect. ChatGPT listing Sixtyfour Intelligence exposes 35 tools here.

Tools

sixtyfour_atlas_file

ChatGPT
Read a bounded UTF-8 chunk from a path returned by Atlas inspect.

sixtyfour_atlas_inspect

ChatGPT
Read an Atlas summary or page of findings, links, or files.

sixtyfour_atlas_list

ChatGPT
List Atlas investigations; continue with next_cursor.

sixtyfour_atlas_start

ChatGPT
Start billable open-ended Atlas research on one subject, then poll sixtyfour_atlas_status.

sixtyfour_atlas_status

ChatGPT
Poll an Atlas task; completion points to sixtyfour_atlas_inspect.

sixtyfour_check_balance

ChatGPT
Return the current credit balance for the configured API key. No arguments required. Returns the number of credits available to spend.

sixtyfour_company_bulk_intelligence_start

ChatGPT
Start an async bulk Company Intelligence job over many companies and return a task_id. Do not return the task_id as your final answer — poll sixtyfour_enrichment_job_status to completion first. Use this to research the same custom struct for many companies at once — e.g. the companies you assembled from company searches. Provide the companies as either rows (a list of dicts of known identifiers like company_name, website, domain, linkedin) or csv_text (a CSV string with a header row), but not both. The server builds the upload file from your input. struct is required. Use find_people with people_focus_prompt and lead_struct for targeted people discovery, or full_org_chart for broad org visibility. The start response includes estimated_cost_credits, a floor estimate (extras like find_people can bill more). Poll the returned task_id with sixtyfour_enrichment_job_status; the completed response includes signed download URLs for the result files and the total charge_credits. This is a billable job — if a start call times out, do not blindly retry, since the job may already have been created. Practical note: companies passed inline travel in the model's context, so this tool is best for up to a few hundred rows assembled from searches. For larger user CSVs, use the Sixtyfour web dashboard or call the bulk API directly. Args: struct: Company output fields to research for every company. rows: Companies to enrich, one dict per company. Provide rows or csv_text, not both. csv_text: CSV text (with header) to enrich, as an alternative to rows. find_people: Whether to discover associated people for each company. people_focus_prompt: Criteria for people discovery when find_people is true. lead_struct: Output schema for each discovered person. full_org_chart: Return a compact org chart grouped by department. research_plan: Optional methodology for where/how to research. tier: Research depth/cost tier: micro, low, medium, or high. field_confidence: Return a confidence score per output field. columns: Subset of input columns to feed the agent. Defaults to all. result_formats: Saved result formats: "csv" (always produced) and/or "ndjson" (preserves typed values). save_json: Also save JSON output artifacts. webhook_url: Optional HTTPS webhook for completed results.

sixtyfour_company_explore_field_values

ChatGPT
Return top values for a categorical field, ranked by company count. Use to discover valid filter values (e.g. exact industry names, country codes) before searching. Each returned value includes a filter_snippet ready to use in a search query.

sixtyfour_company_get_company_details

ChatGPT
Return expanded details for one company from search results. Without include_fields, returns fields derived from the original search context. With include_fields, returns identity fields plus the requested fields (use dot-notation for nested fields, e.g. "key_executives.member_full_name"). Max 20 fields.

sixtyfour_company_get_searchable_fields

ChatGPT
Return every searchable field, nested path, query limit, and supported operator. Call once at the start of a session. Use the returned field names exactly in queries — unknown fields cause errors. Nested fields (e.g. funding_rounds.amount_raised) require $elemMatch when queried.

sixtyfour_company_intelligence_start

ChatGPT
Start an async Company Intelligence job and return a task_id for polling. Do not return the task_id as your final answer — poll sixtyfour_enrichment_job_status to completion first. Use this to enrich one company. target_company should contain identifiers such as company_name, website, domain, LinkedIn URL, or location. struct is required. Each key becomes a field in structured_data. Each value can be a plain-English description or an object like {"description": "Approximate employee count", "type": "int"}. Use find_people with people_focus_prompt for targeted people discovery. Use full_org_chart for broad department-level employee visibility. Example struct: { "company_name": "Name of the company", "industry": "Primary industry", "employee_count": {"description": "Approximate employee count", "type": "int"}, "uses_shopify": "True if the company uses Shopify" } Args: target_company: Company identifiers. struct: Company output fields to research and return. find_people: Whether to discover associated people. people_focus_prompt: Criteria for people discovery, e.g. "Find the CTO and VP of Marketing". lead_struct: Output schema for each discovered person. research_plan: Optional methodology for where/how to research. tier: Research depth/cost tier: micro, low, medium, or high. full_org_chart: Whether to return a compact org chart grouped by department.

sixtyfour_company_next_page

ChatGPT
Fetch the next page of results from a previous company search. Returns the same shape as sixtyfour_company_search (with result_handles, previews, and a new next_cursor if more pages exist). Cursors expire after ~20 minutes; if expired, rerun the original search. Billable: 0.1 credit per result returned (a 100-row page costs 10 credits). Each response includes charge_credits, the amount charged for that page.

sixtyfour_enrich_linkedin

ChatGPT
Enrich one LinkedIn profile synchronously and return the result directly. This is a billable synchronous call (no task_id, no polling). If it times out, do not blindly retry because the upstream API may still have charged the request.

sixtyfour_enrichment_job_status

ChatGPT
Poll an async enrichment job by task_id. Pass the task_id returned by any async enrichment start tool: sixtyfour_people_intelligence_start, sixtyfour_company_intelligence_start, sixtyfour_people_bulk_intelligence_start, sixtyfour_company_bulk_intelligence_start, sixtyfour_find_email_start, sixtyfour_find_phone_start, sixtyfour_reverse_email_start, or sixtyfour_reverse_phone_start. To cut the number of calls you make, pass wait_seconds (up to 25): the server blocks until the job is terminal or the wait elapses, then returns. While status is running, wait ~10s and call this tool again with the same task_id; only stop on a terminal status (completed, failed, cancelled, terminated, timed_out). Do not answer the user while the job is still running. Completed responses include the upstream result and charge_credits inside data. Bulk intelligence jobs return signed download URLs under data.results; non-bulk enrichment jobs return inline data under data.result and usually include task_type. Args: task_id: The task_id returned by an async enrichment start tool. wait_seconds: Seconds to block server-side until terminal (0 = return immediately, max 25).

sixtyfour_find_email_start

ChatGPT
Start an async bulk find-email job and return a task_id for polling. Do not return the task_id as your final answer — poll sixtyfour_enrichment_job_status to completion first. Discovers email addresses for 1-100 leads in one billable job. Best results need more than a name. If a lead only has a person's name, first use people search, get the person details, then include their LinkedIn URL, current company, or company domain before calling this tool. This guidance applies to both PROFESSIONAL and PERSONAL modes. Poll the returned task_id with sixtyfour_enrichment_job_status; the completed result contains the enriched leads with discovered emails. Args: leads: Leads to process (1-100). For a single lead, pass a list of one. verify_emails: SMTP-verify each discovered email before returning it. mode: Email type to discover: PROFESSIONAL (work) or PERSONAL.

sixtyfour_find_phone_start

ChatGPT
Start an async bulk find-phone job and return a task_id for polling. Do not return the task_id as your final answer — poll sixtyfour_enrichment_job_status to completion first. Discovers phone numbers for 1-100 leads in one billable job. Best results need more than a name. If a lead only has a person's name, first use people search, get the person details, then include their LinkedIn URL, current company, or company domain before calling this tool. Poll the returned task_id with sixtyfour_enrichment_job_status. Args: leads: Leads to process (1-100). For a single lead, pass a list of one.

sixtyfour_find_similar_results

ChatGPT
Page the ranked matches of a completed similarity search. Pass search_id for the first page, then the returned next_cursor (without search_id) for later pages. Each row carries a 0-100 similarity score, its rank, and the matched signals explaining why the person is similar. Billable per returned row.

sixtyfour_find_similar_start

ChatGPT
Find people similar to seed profiles (lookalike search) — "more people like these". Seeds come from linkedin_urls (1-1000 profile URLs) or csv_text — the full raw text of the user's seed file. When the user points at a file or a vague list, read it and pass ALL of it rather than a few sampled URLs: more seeds produce a better similarity cohort. The cohort's defining traits (roles, skills, industry, seniority, ...) are inferred automatically; pass guidance ONLY for hard requirements the user explicitly stated. Async and billable: capture task_id, poll sixtyfour_find_similar_status until completed, then page ranked people with sixtyfour_find_similar_results. Seed profiles are always excluded from results.

sixtyfour_find_similar_status

ChatGPT
Check a similarity search started with sixtyfour_find_similar_start. Poll until status is completed (typically 1-3 minutes); pass wait_seconds (up to 25) to block server-side and save round-trips. On completed, take search_id from the response and call sixtyfour_find_similar_results. Do NOT poll this task_id with sixtyfour_enrichment_job_status.

sixtyfour_get_feedback

ChatGPT
Read your feedback and its received, reviewed or fixed status. Free. Check later; do not poll in a loop.

sixtyfour_people_bulk_intelligence_start

ChatGPT
Start an async bulk People Intelligence job over many leads and return a task_id. Do not return the task_id as your final answer — poll sixtyfour_enrichment_job_status to completion first. Use this to research the same custom struct for many people at once — e.g. the leads you assembled from people searches. Provide the leads as either rows (a list of dicts of known identifiers like name, company, title, linkedin) or csv_text (a CSV string with a header row), but not both. The server builds the upload file from your input. struct is required. Each key becomes a field in the enriched output. Each value can be a plain-English description or an object like {"description": "Primary work email address", "type": "str"}. The start response includes estimated_cost_credits, a floor estimate. Poll the returned task_id with sixtyfour_enrichment_job_status; the completed response includes signed download URLs for the result files and the total charge_credits. This is a billable job — if a start call times out, do not blindly retry, since the job may already have been created. Practical note: leads passed inline travel in the model's context, so this tool is best for up to a few hundred rows assembled from searches. For larger user CSVs, use the Sixtyfour web dashboard or call the bulk API directly. Args: struct: Output fields to research for every lead. rows: Leads to enrich, one dict per lead. Provide rows or csv_text, not both. csv_text: CSV text (with header) to enrich, as an alternative to rows. research_plan: Optional methodology for where/how to research. tier: Research depth/cost tier: micro, low, medium, or high. field_confidence: Return a confidence score per output field. columns: Subset of input columns to feed the agent. Defaults to all. result_formats: Saved result formats: "csv" (always produced) and/or "ndjson" (preserves typed values). save_json: Also save JSON output artifacts. webhook_url: Optional HTTPS webhook for completed results.

sixtyfour_people_explore_field_values

ChatGPT
Return top values for a categorical people field, ranked by profile count. Use to discover valid filter values before searching. Args: field: Field name from sixtyfour_people_get_searchable_fields. top_k: Max distinct values to return. scope: A simple_filters dict to narrow the population before aggregating.

sixtyfour_people_get_person_details

ChatGPT
Return expanded details for one person from search results. Without include_fields, returns fields derived from the original search context. With include_fields, returns identity fields plus the requested fields. Max 20 fields. Args: result_handle: The result_handle from a search result item. Expires after ~20 minutes; rerun search if expired. include_fields: Field names from sixtyfour_people_get_searchable_fields.

sixtyfour_people_get_searchable_fields

ChatGPT
Return every searchable field, nested path, query limit, and supported operator for people profiles. Call once at the start of a session. Use the returned field names exactly in queries — unknown fields cause errors.

sixtyfour_people_intelligence_start

ChatGPT
Start an async People Intelligence job and return a task_id for polling. Do not return the task_id as your final answer — poll sixtyfour_enrichment_job_status to completion first. Use this to enrich one person or lead. lead_info should contain any known identifiers such as name, email, company, title, location, website, or LinkedIn URL. struct is required. Each key becomes a field in structured_data. Each value can be a plain-English description or an object like {"description": "The individual's primary work email", "type": "str"}. Example struct: { "name": "The individual's full name", "email": {"description": "Primary work email address", "type": "str"}, "linkedin": "LinkedIn URL for the person", "github_notes": "Detailed notes on their GitHub profile" } Args: lead_info: Lead identifiers. struct: Output fields to research and return. research_plan: Optional methodology for where/how to research. tier: Research depth/cost tier: micro, low, medium, or high.

sixtyfour_people_next_page

ChatGPT
Fetch the next page of results from a previous people search. Returns the same shape as sixtyfour_people_search. Cursors expire after ~20 minutes; if expired, rerun the original search. Args: cursor: The next_cursor value from a sixtyfour_people_search or sixtyfour_people_next_page response. Billable: 0.1 credit per result returned (a 100-row page costs 10 credits). Each response includes charge_credits, the amount charged for that page.

sixtyfour_reverse_email_start

ChatGPT
Start an async bulk reverse-email lookup job and return a task_id for polling. Do not return the task_id as your final answer — poll sixtyfour_enrichment_job_status to completion first. Resolves the person behind each email address for 1-100 leads in one billable job. Each lead must include an email field. Poll the returned task_id with sixtyfour_enrichment_job_status. Args: leads: Leads to process (1-100), each with an email field.

sixtyfour_reverse_phone_start

ChatGPT
Start an async bulk reverse-phone lookup job and return a task_id for polling. Do not return the task_id as your final answer — poll sixtyfour_enrichment_job_status to completion first. Resolves the person behind each phone number for 1-100 leads in one billable job. Each lead must include a phone field. Poll the returned task_id with sixtyfour_enrichment_job_status. Args: leads: Leads to process (1-100), each with a phone field.

sixtyfour_send_feedback

ChatGPT
Report a wrong result, missing data, or a product problem to Sixtyfour. Send at least one of rating, message or fields. Use a returned task_id or a workflow row as target; omit target for general problems. Free. This records a report, not a correction to the underlying data. Keep the returned id to check received/reviewed/fixed status with sixtyfour_get_feedback.

sixtyfour_send_test_webhook

ChatGPT
Send a synthetic Sixtyfour event to a user-specified public HTTPS URL. First list events with sixtyfour_webhook_test_events. Only send when the user asks to test their receiver. Uses the caller's org signing configuration; required refuses unsigned delivery. Free; runs no enrichment, monitor or workflow. Test-marked callbacks can trigger receiver side effects. May take 100 seconds. Do not retry automatically: another call sends another event. Inspect data.delivered for delivery outcome. Sample ids are not real resources.

sixtyfour_verify_age_start

ChatGPT
Start an async Age Verification job and return a task_id for polling. Do not return the task_id as your final answer — poll sixtyfour_verify_age_status to completion first. Establishes a person's date of birth (or a grounded age estimate when an exact date isn't available) from open-source research, with per-field confidence and sourced evidence. subject should contain any known identifiers such as name, company, LinkedIn URL, email, or location — more is better.

sixtyfour_verify_age_status

ChatGPT
Poll an async Age Verification job by task_id. Pass the task_id returned by sixtyfour_verify_age_start. To cut the number of calls you make, pass wait_seconds (up to 25): the server blocks until the job is terminal or the wait elapses, then returns. While status is running, wait ~10s and call this tool again with the same task_id; only stop on a terminal status (completed, failed, cancelled, terminated, timed_out). Do not answer the user while the job is still running. Completed responses include date_of_birth (day/month/year/confidence), age (value/as_of/confidence), evidence, and sources directly under data — this is a dedicated envelope, not the generic enrichment job-status shape.

sixtyfour_webhook_test_events

ChatGPT
List webhook contracts and synthetic examples, including monitor and workflow events. Pass type to return only that example payload. Free; sends nothing.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/plugin_asdk_app_6a514c90130c8191bb9a04df335d5ac6"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/plugin_asdk_app_6a514c90130c8191bb9a04df335d5ac6)