Use Pioneer With Your Agent

Everything Pioneer does can be driven by an agent through the API. Instead of clicking through pipelines yourself, you tell your agent what you are looking for, and it creates the pipeline, reads the researched leads, and works the board on your behalf.

Connect Claude.ai directly (MCP)

If you use claude.ai (the web app), you can connect Pioneer as a custom connector through its MCP server. No API calls, no terminal, no skill file needed.

How to connect

1. Create an API key on your API Keys page (account menu → API Keys → Create key)
2. Copy the connector URL shown right after creation. It looks like https://usepioneer.ai/api/mcp/pioneer_sk_.../mcp
3. In claude.ai, go to Settings → Connectors → Add custom connector and paste the URL

That's it. Claude can now create pipelines, read leads, and work your board on your behalf.

The URL contains your API key. Treat it like a password: never paste it into a shared conversation, never commit it, and revoke the key on the API Keys page if it leaks.

The MCP server is a protocol adapter

The MCP server translates Pioneer's API into the MCP protocol that claude.ai speaks. Every tool it exposes maps to one API endpoint; there is no extra capability you can reach through MCP that you cannot reach through the API directly. If you prefer the direct API (for use with Claude Code, Codex, Devin, or custom agents), the same key works for both.

Which agents work

Any agent that can make an HTTP request with a bearer token can use Pioneer. That includes, among others:

• Claude.ai (web app): connect via the MCP connector URL above
• Claude Code: use the API directly with a bearer token
• OpenAI Codex: use the API directly
• Devin: use the API directly
• Hermes: use the API directly
• Cursor and other coding agents: use the API directly
• Custom agents: use the API directly

Every agent path uses the same API key. There is nothing Pioneer-specific to install: if your agent can run curl or issue an HTTP request, it can run Pioneer today.

API or MCP? Use the HTTP API when your agent can make requests directly, as Claude Code, Codex, Devin, Hermes, and custom agents can: it is simpler, adds no extra process, and the full reference is one page. Use MCP when your assistant only accepts connectors, as claude.ai and some chat-first tools do. The tool-to-route map, the inspector command, and the OAuth caveat live in the API reference.

Best practice: put Pioneer in a skill

Do not re-explain Pioneer to your agent every session. Save it once as a skill, the reusable instruction file most harnesses support (.claude/skills/, .agents/skills/, AGENTS.md, a custom prompt library, whatever yours uses), and the agent picks it up automatically from then on.

A good Pioneer skill does four things:

1. Says where the key lives. Read it from an environment variable such as PIONEER_API_KEY. Never paste a key into the skill file itself, and never commit it.
2. Tells the agent how to get a key when there is none. It has to walk the user through creating one in the app (API Keys), because no agent can mint one.
3. Points at the API reference. /docs/api is the whole contract: base URL, auth, endpoints, conventions. The skill should say to read it rather than guess routes.
4. Names the job. "Find and qualify leads matching X, keep the board current, report new relevant leads" beats a generic "use the Pioneer API".

Here is a skill you can copy as-is:

# Pioneer (lead research)

Use Pioneer to find and qualify leads: https://usepioneer.ai/docs/api is the
full API reference. Read it before calling anything.

## Auth
Send `Authorization: Bearer $PIONEER_API_KEY` against https://usepioneer.ai/api/v1.
If `PIONEER_API_KEY` is unset, or a call returns 401/403, stop and ask the user
to create or fix the key in the app: account menu, then API Keys, then Create
key. The key is shown once, and every plan including the free tier can create
one. Never print the key back to them.

## How to work
- One pipeline per goal, phrased specifically: POST /pipelines { "goal": "..." }.
- Read results with GET /pipelines/{id}/leads, and one lead in full with
  GET /leads/{entryId}.
- Act on leads with PATCH /leads/{entryId} (status, bucketId). That judgment is
  what teaches the pipeline, so record it rather than keeping it in chat.
- Wrong researched value: POST /leads/{entryId}/mark-inaccurate.
  Missing value: POST /leads/{entryId}/search-more.
- Async endpoints return 202. Poll the matching GET, no faster than every 2s.
- Explain results to the user in their terms. Do not make them read the docs.

Once that file exists, "check Pioneer for new leads on the EU climate pipeline" is a complete instruction.

What to hand your agent, and what to keep

Give your agent the API key and the goal. Keep the judgment: which leads are worth pursuing is the part Pioneer is built to hand back to you, and every approval or rejection your agent records on your behalf should be one you would have made yourself.

Start with the API reference. If you want to understand what your agent is actually doing, Your Pipeline & Board explains the product it is driving.