Easeclaw

io.github.priteshmannPublished by GitHub account priteshmannv1.0.0Updated Oct 25, 2026

AI lead-finder for agents: pull scored leads, draft replies in your voice, work the pipeline.

VerifiedStreamable HTTPWeb executableCommunication & CollaborationBusiness & Commerce

Overview

AI-generated overview

EaseClaw is a remote MCP server that lets an assistant pull scored sales leads, read their source posts, draft replies in your voice, and update your pipeline.

What you can do
List projects and leads, and read a single lead with its details and source posts, scored by buying intent. Draft replies in your voice for a lead. Update lead records and review recent activity across the pipeline. The assistant cannot post or send anything; you review and send every reply yourself.
When to use it
Use it when you run lead generation or outreach through EaseClaw and want an assistant to triage warm leads, summarize source posts, and prepare reply drafts for your review.
Requirements
A remote MCP endpoint reached over streamable HTTP, with an OAuth-based Authorization bearer API key minted from your EaseClaw account; an EaseClaw plan is required. Network access to the EaseClaw service.
Before you install
Requires an EaseClaw API key sent in the Authorization header, and a paid plan. The server can update lead records, so changes to your pipeline data should be reviewed. Replies are drafted only and must be sent by you; the README states the agent can never post.

Installation

In SourceWeft

  1. Open Easeclaw in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.priteshmann%2Feaseclaw/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "easeclaw": {
      "type": "http",
      "url": "https://www.easeclaw.com/api/mcp"
    }
  }
}

README

easeclaw-agent

An agent skill for EaseClaw — the AI lead-finder your agent can drive. Install this skill and your agent (Claude Code, OpenClaw, or anything that reads SKILL.md) can pull warm leads scored by buying intent, read the source posts, draft replies in your voice, and work your pipeline.

Your agent can never post. You review and send every reply. That's the product's hard rule, and Rule 1 of this skill.

Install

sh
npx skills add priteshmann/easeclaw-agent

Then set your key (minted at https://www.easeclaw.com/leads/api):

sh
export EASECLAW_API_KEY=ec_live_...

Or connect the MCP server directly — no skill needed:

sh
claude mcp add --transport http easeclaw https://www.easeclaw.com/api/mcp \  --header "Authorization: Bearer $EASECLAW_API_KEY"

What your agent gets

Six capabilities over MCP or REST (OpenAPI: https://www.easeclaw.com/openapi.json): list_projects, list_leads, get_lead, draft_reply, update_lead, get_activity.

Full usage rules and the core workflow are in SKILL.md.

Source: README.md at commit c7115d9

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts