The USAgentLeads MCP server provides credit-aware access to agent and brokerage lead data via hosted HTTP or a local stdio bridge.
Check catalog coverage, release date, and data limitations without spending record credits.
Count and preview matching agents or brokerages using filters such as state, city, zip, mustHave, activeLicense, organization, and orgType, with no record-credit spend.
Check the shared dashboard/API credit balance.
Read previously unlocked or owned records, up to 100 per page, without spending record credits.
Unlock agent or brokerage records for credits (1 per agent, 2 per brokerage) with a max-credit cap, explicit confirmation, and a saved UUID idempotency key; already-owned and contactless records are free.
Create authenticated CSV export requests for owned records, with templates and suppression-list/audit handling, without spending credits.
Use bearer auth from a protected environment variable; hosted REST and MCP share 60 requests/minute/account and monthly quotas, with limited result and cursor recovery windows.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@usagentleads-mcp find masked contact previews for marketing directors at SaaS firms in Texas"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
The hosted endpoint is https://www.usagentleads.com/api/mcp. Growth and Pro include REST v3 and hosted MCP. The v3 backend is deployed.
Configure Streamable HTTP with an Authorization bearer header from a protected environment variable. OAuth is not included. Never put credentials in a URL or shared prompt.
For the local stdio bridge:
npm ci
export USAGENTLEADS_API_KEY='your-key'
npm startConfigure your client to launch node /absolute/path/usagentleads-mcp/src/index.mjs and provide the key through its environment.
New audience-specific tools return contacts directly: search_agents, search_brokerages, lookup_agents and lookup_brokerages. Count/preview tools, get_account, get_usage, search_locations and get_request spend no record credits. create_contact_export queues new or owned records; export_status, export_download and cancel_export manage the job.
lookup_agents accepts either ids or a name with optional filters (state, city, organization and contact availability), limit and cursor. Name matching is a case-insensitive literal substring and may return multiple candidates. Use preview_agents with filters.name to review IDs, city and brokerage before approving acquisition. count_agents, search_agents and agent exports also accept filters.name. Use mustHave: ["fullAddress"] to require a complete recorded business address. lookup_brokerages remains ID-only.
Billable tools require max_credits, a saved UUID idempotency_key and confirm_credit_spend:true. Obtain authorization for the selection and cap first. New agents cost 1 credit and brokerages 2; repeat ownership is free across dashboard, REST and MCP. A timeout is not permission to use a new key.
Export download returns an authenticated URL without credentials. REST and hosted MCP share 60 requests/minute/account and monthly quotas. Results are recoverable for 30 days; cursors last 24 hours.
Run npm test for offline client/protocol checks. The app's bun scripts/generate-api-v3-docs.mjs synchronizes tools.json with hosted MCP schemas.
Documentation: https://www.usagentleads.com/docs. MIT covers client code, not the licensed dataset.
Count matching agents or brokerages. Searching spends no record credits.
Inputs: kind (required), filters.
Get release date, catalog coverage and data limitations. No record credits spent.
Inputs: no named parameters.
Prepare an authenticated CSV download request for owned records. The download applies your suppression list and records an export audit. No credits spent; do not include your API key in a URL.
Inputs: kind (required), list, template.
Check the shared dashboard/API credit balance.
Inputs: no named parameters.
Read previously unlocked records. No record credits spent. Returns at most 100 records per page.
Inputs: q, kind, list, page, +1 more.
Preview masked agents or brokerages. Searching spends no record credits.
Inputs: kind (required), filters.
SPENDS CREDITS: one per agent, two per brokerage. Obtain the user's approval for the exact selection and maxCredits before calling. Reuse the SAME UUID idempotencyKey and parameters on retries; never automatically create a new key after a timeout. Already-owned and contactless records cost zero.
Inputs: kind (required), releaseId (required), maxCredits (required), idempotencyKey (required), +4 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 7 tools
Each tool targets a distinct stage of the lead-data workflow: metadata, counting, masked preview, balance, owned records, unlocking, and export. The no-credit tools (count_records, preview_records, coverage) are clearly differentiated by output type, and unlock_records is clearly separated from preview_records by cost and result.
All names use snake_case and are readable, but the pattern is not uniformly verb_noun: owned_records is adjective_noun, while coverage and credit_balance are noun phrases. The deviations are minor and still predictable within the domain.
Seven tools is well-scoped for a lead-data marketplace, with each tool earning its place by covering a distinct workflow step. There is no obvious redundancy or missing operational layer that would require more tools.
The surface covers the core lifecycle: coverage check, count, preview, credit balance, unlock, read owned records, and export. Minor gaps exist around suppression-list management and export history/status, but agents can work around these for the main purchase workflow.
Search B2B contacts and business leads through an OAuth-secured MCP server with masked results.
Search and update Records and Lists, import and export CSVs, and run enrichment in Connie.
Authenticated public evidence search, verification, research jobs, exports, and webhooks.
Enrich and search people and companies, resolve identities, and enrich IP addresses.
