For AI agents · MCP + REST API
The lead-finding MCP server for your AI agent
Connect Claude Code, Cursor, or any MCP client. Your agent pulls warm leads scored by buying intent, drafts the reply in your voice, and works your pipeline — end to end. The one thing it can never do is press send. That’s yours.
One command · Claude Code
claude mcp add --transport http easeclaw https://www.easeclaw.com/api/mcp \ --header "Authorization: Bearer ec_live_YOUR_KEY"
Included with every EaseClaw plan · read & draft only — never posts
Connect your agent
Mint a key at easeclaw.com/leads/api (shown once, revoke anytime), then pick your client.
Claude Code — one command
claude mcp add --transport http easeclaw https://www.easeclaw.com/api/mcp \ --header "Authorization: Bearer ec_live_YOUR_KEY"
Cursor — .cursor/mcp.json
{
"mcpServers": {
"easeclaw": {
"url": "https://www.easeclaw.com/api/mcp",
"headers": { "Authorization": "Bearer ec_live_YOUR_KEY" }
}
}
}Anything else — plain REST
curl -H "Authorization: Bearer ec_live_YOUR_KEY" \ "https://www.easeclaw.com/api/v1/leads?min_score=70&limit=10"
Six tools. The whole loop.
Most lead tools’ agent integrations stop at reading mentions. EaseClaw’s MCP closes the loop — your agent works a lead end to end. Except one step.
Find
list_leadsWarm leads scored 40–100 by buying intent, best first — filter by project, status, score, or time.list_projectsWhat's being monitored: website, buyer-intent keywords, sources.Read
get_leadThe complete source post, the score and its reasoning, the current draft.get_activityRecent monitoring runs — what was scanned, what qualified.Draft
draft_replyA reply in the owner's voice — steer with tone, length, a revision note, or up to 3 variants. Uses the plan's daily AI budget.Track
update_leadWork the pipeline — new / saved / dismissed / contacted / won / lost — or write back an edited draft.Send
No tool exists for this step. Your agent hands you the draft and the permalink; you read it, tweak it, and send it yourself. That’s the product rule that keeps your outreach human.
Prefer plain HTTP?
The same key works on the REST API — for scripts, n8n, Zapier webhooks, anything. Full schema in the OpenAPI spec.
| GET /api/v1/leads | List warm leads — project_id, status, min_score, since, limit |
| GET /api/v1/leads/:id | One lead in full |
| PATCH /api/v1/leads/:id | Update status and/or write back an edited draft_reply |
| POST /api/v1/leads/:id/draft | Generate a reply draft — tone, length, note, n |
| GET /api/v1/projects | Monitored projects |
| GET /api/v1/activity | Recent monitoring runs |
Bearer auth · 300 requests/hour per account · drafting capped by your plan’s daily AI budget.
Questions
What is an MCP server?
MCP (Model Context Protocol) is the open standard AI agents use to talk to tools. Adding EaseClaw's MCP server gives your agent — Claude Code, Claude Desktop, Cursor, or any MCP client — direct access to your leads: it can list them, read the source posts, generate reply drafts, and update pipeline status.
Can my agent post or send replies for me?
Never. The MCP server is read-and-draft only: there is no tool that posts, sends, or messages anyone. Your agent prepares the work; you review and send every reply yourself. That's a hard product rule, not a setting.
What does it cost?
The MCP server and REST API are included with every EaseClaw plan ($49, $99 or $199/mo — $9 7-day trial on Starter and Pro). Reply drafting uses your plan's daily AI budget, which is hard-capped, so an agent loop can never run up a surprise bill.
Which tools does my agent get?
Six: list_projects, list_leads, get_lead, draft_reply, update_lead, and get_activity. Together they cover the full loop — find the lead, read the post, draft the reply in your voice, and move it through your pipeline (saved, contacted, won, lost).
How is it secured?
You mint an API key in your dashboard (only a hash is stored — the key is shown once). Requests are rate-limited to 300/hour per account, drafting is budget-capped, and you can revoke a key at any time — anything using it stops working immediately.
How is this different from other lead tools' MCP servers?
Most agent integrations in this space stop at reading mentions or scoring posts. EaseClaw's MCP closes the loop: the same connection that finds and scores the lead also drafts the reply in your voice and updates your pipeline — your agent can work leads end to end, except pressing send.
Give your agent a pipeline.
Start the $9 trial, mint a key, and your agent is pulling scored leads two minutes from now.