agentleFS
LeadMagicLeadMagic/leadmagic-skills/skills/mcp-integration/SKILL.md

mcp-integration

Skill0 starsChanged 4 months agoMITView on GitHub

LeadMagic hosted MCP setup for Claude Code, Claude Desktop, Cursor, Windsurf, and VS Code. Use when installing the LeadMagic MCP server at mcp.leadmagic.io, configuring OAuth, choosing between MCP and REST, or mapping MCP tools to REST enrichment endpoints.

23 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use results-report, daily-coding and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Galaxy-DawnSkill

    results-report

    This skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment retrospection", "write a results report", "写实验总结报告", "写实验复盘", or mentions turning completed experiment artifacts into a structured, decision-oriented research report. It assumes strict analysis should come from `results-analysis` first.

    Also in 3 projects that use this

  • Clay-HHKSkill

    daily-coding

    Daily coding assistant that auto-triggers when writing/modifying code, providing a core checklist.

    Also in 3 projects that use this

  • Clay-HHKSkill

    kaggle-learner

    This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.

    Also in 3 projects that use this

  • kharlamenkodevSkill

    bug-detective

    Also in 3 projects that use this

  • indranilbanerjeeSkill

    review-response

    Draft a reply to one customer review, voice-scored, with escalation flags. \"reply to this 1-star review\"

    Also in 3 projects that use this

  • Google CloudSkill

    citation-verification

    Verify that citations in a document resolve to real records and that claimed titles match. Use before trusting a document's reference list.

    Also in 3 projects that use this

  • +2 more from Clay-HHK

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 22 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Prefer the hosted MCP over hand-rolled curl in agent sessions: OAuth (no key in shell history), server-side token handling, and composite …

    line 18
  2. Very specific:

    Prefer composites (account_intel, enrich_contact, find_decision_makers) over long primitive chains.

    line 73

“Common” is measured: kept by at least 6 in 10 of the 22 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

LeadMagic — MCP integration

Prefer the hosted MCP over hand-rolled curl in agent sessions: OAuth (no key in shell history), server-side token handling, and composite tools that replace multi-call chains.

Config

Claude Code: claude mcp add --transport http leadmagic https://mcp.leadmagic.io/mcp

Cursor configuration (other clients use their own formats; consult the setup docs):

{
  "mcpServers": {
    "leadmagic": { "url": "https://mcp.leadmagic.io/mcp" }
  }
}

Claude web / desktop custom connector: URL https://mcp.leadmagic.io/mcp. Per-client steps: mcp.leadmagic.io/clients.

New users: sign up at app.leadmagic.io, run one thing in the app (e.g. a first sheet in Sheet Enrichment — see the sheets skill), then connect the MCP. OAuth signs the client into a workspace; pick the one that owns the user's sheets and credits.

Complete OAuth in the browser on first use. 401 later → reconnect OAuth in the client (do not add a REST API key to this OAuth configuration). 402 → credits/billing.

Tool → REST map (core)

MCP toolREST equivalent
check_credit_balance / preview_costGET /v1/credits / POST /v1/batch/preview-cost (free)
find_work_email / validate_work_emailemail-finder / email-validation
find_personal_email / find_mobile_numberpersonal-email-finder / mobile-finder
b2b_profile_to_work_email / linkedin_profile_to_work_email / email_to_b2b_profileb2b-profile-email / b2b-profile
search_profile / enrich_contactprofile-search (+composite)
search_people / find_people_by_role / find_company_employeesv3 people search / role-finder / employee-finder
enrich_companycompany-search
research_account / account_intelMCP account snapshot / research composites (no single REST equivalent)
find_company_funding / get_company_technographicscompany-funding / technographics
find_lookalike_companiesv3 lookalike
find_decision_makersrole/employee composite
find_jobs / search_jobsjobs search
get_company_hiring_signals/v1/jobs/companies/{domain}/hiring-signals
detect_job_changejob-change-detector
find_local_leadsPOST /bulk/local-leads
submit_detected_bulk_job / process_attached_csv / get_bulk_job_status / watch_bulk_job_progress / pause_bulk_job / resume_bulk_job / restart_bulk_job / export_bulk_job/bulk/*
get_account_analytics/v1/analytics/* (free)
list_sheets / get_sheet / add_sheet_columns / run_sheet_column / read_sheet_rows (+ ~40 more)Sheets (MCP + app only, no public REST) — see the sheets skill

Ads and competitor tools are currently paused on hosted MCP. Custom HTTP request columns are configured and run in the LeadMagic app; hosted MCP exposes no arbitrary outbound HTTP tools.

Sheets tools only appear when the signed-in workspace has Sheets (paid plan). If they're missing, check the plan and the workspace chosen during OAuth, then reconnect.

Usage rules

  • Prefer composites (account_intel, enrich_contact, find_decision_makers) over long primitive chains.
  • Who holds one role or title at a company → find_people_by_role first (2 credits if found, free on a miss). Use search_people or find_company_employees only for lists; if Role Finder finds no one, report the miss instead of searching for the role.
  • Free first: check_credit_balance + preview_cost before expensive or bulk work.
  • One record → single tools; CSV/list → bulk path or a sheet; poll get_bulk_job_status ≥45s apart.
  • Single-record lookups run directly. Every paid sheet run, including small samples, runs of 5 credits or less, and AI using the user's own provider key, requires an exact quote and explicit user approval. Only verified free sheet runs (zero LeadMagic credits and no external provider billing) start immediately; unknown quotes cannot start. Bulk jobs, paid sheet runs, imports, pushes, and deletes return needs_confirmation + confirmation_token first. Show the credit cost and provider billing summary, resend the identical arguments with the token only after the user agrees, and never invent a token.
  • Claude Code names plugin-bundled tools mcp__plugin_leadmagic_leadmagic__<tool> and hand-added ones mcp__leadmagic__<tool>. Permission rules and hooks must match both (the plugin's approval hook does).
  • Pass company_domain (e.g. stripe.com) when identifying companies.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.