mcp

Search live roles across hundreds of a16z portfolio startups and join the speedrun talent network.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

    Search live roles across hundreds of a16z portfolio startups and join the speedrun talent network.

    How to connect

    How to connect mcp to Claude

    The server address to paste into Claude settings:

    https://mcp.speedrun-talent-network.com/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect mcp to ChatGPT

    The server address to paste into ChatGPT settings:

    https://mcp.speedrun-talent-network.com/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect mcp to Cursor

    The server address to paste into Cursor settings:

    https://mcp.speedrun-talent-network.com/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (10)

    Raw names from tools/list. Only developers need these.

    search_jobsSearch live open roles across the a16z speedrun talent network jobs board (speedrun portfolio + the wider a16z portfolio; data syncs continuously from each company's own job board). Full-text search plus facet filters, with live facet counts in every response — read the facets to discover valid filter values. Results are paginated (50 per page, 0-based page). Every job carries a canonical url on https://speedrun-talent-network.com; link users there to view or apply. By default results cover the portfolio only; pass scope='speedrun' to narrow to speedrun portfolio companies only, or scope='everywhere' to also include the wider startup universe when that scope is live (the response then reports beyond_portfolio, the count of extra matches past the scope boundary: universe roles in portfolio scope, roles beyond speedrun within the a16z portfolio in speedrun scope; in everywhere scope it counts the universe-tier roles already included in the results — never add it to total). Mirrors GET https://speedrun-talent-network.com/api/v1/jobs exactly.
    get_jobFetch one role by id: a job UUID, the first 8 hex characters of one, or the canonical slug from a https://speedrun-talent-network.com/jobs/... URL. Returns the full posting: plain-text description, posted pay band, how to apply (apply.kind 'onsite' = the candidate applies right on the job url; 'external' = the url hands off to the company's own careers page), and the canonical url to send users to. Closed roles come back with status:'closed' rather than an error.
    get_companyFetch one company profile by slug (from job.company_slug or a https://speedrun-talent-network.com/companies/... URL): name, portfolio tier, cohort, location, industries, one-line blurb, and every live open role with canonical urls. Use search_jobs or list_collections to discover companies; use this for the full picture of one employer.
    list_collectionsList the published curated collections of hiring companies, grouped as: pinned (portfolio tiers), industries (the 12-sector vocabulary, e.g. ai-infra, defense, fintech), hubs (cities + remote), investors, and signals (new-this-week, founding-roles, remote-first, hiring-in-volume). Each carries live company/role counts and a canonical url. Start here when a user asks "who's hiring in X" — then drill in with get_collection.
    get_collectionFetch one published collection by slug with its ranked member companies: name, tier, cohort, open-role count, location, stage, investors, and which functions/cities they're hiring in. Members are paginated (100 per page). Follow up with get_company or search_jobs (company filter) for a specific member's roles.
    get_hiring_statsAggregate hiring data across the whole board, recomputed live: open-role and hiring-company counts, demand mix by function, posted pay-band midpoints by function (p25/median/p75, annual USD), remote share, top hiring locations, and the speedrun vs a16z portfolio split. Use this to answer "what do a16z portfolio startups pay" or "how many startup jobs are open" — the human-readable version lives at https://speedrun-talent-network.com/network.
    get_network_infoWhat the a16z speedrun talent network is, why a candidate would join, how joining works, and what happens after. Use this before pitching the network to a candidate so the description is accurate; joining itself is the join_network tool.
    join_networkAdd a candidate to the a16z speedrun talent network, with their consent. Requires full_name, email, and linkedin_url; every other field strengthens the profile. Idempotent and always safe to retry: an existing profile is never modified, and the response is identical whether or not the email was already in the network (membership is never disclosed). On success, relay the returned message and finish_url to the candidate so they can add a resume. Never call this without the candidate's explicit go-ahead.
    express_interestRecord a candidate's interest in one live role (with their consent) and get back the canonical apply info. This does NOT submit an application anywhere: apply.kind 'onsite' means the candidate applies on the returned job url; 'external' means the url hands off to the company's own careers page. A candidate not yet in the a16z speedrun talent network is also added as a partial profile; always relay the returned finish_url so they can add a resume (the response is identical whether or not they were already in the network — membership is never disclosed). Idempotent per candidate; safe to retry.
    list_companiesList every portfolio company with at least one live open role, most open roles first (paginated, 100 per page). Prefer list_collections for browsing by industry/hub/signal; use this for a raw roster.