Speedrun Talent Network MCP Server

Fetch 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.

List 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.

List 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.

Fetch 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.

Record 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 (relay the returned finish_url so they can add a resume). Idempotent per candidate; safe to retry.

Aggregate 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.

Fetch 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.

Search 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='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 portfolio boundary). Mirrors GET https://speedrun-talent-network.com/api/v1/jobs exactly.

Add 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: a candidate who is already in the network gets already_member (missing fields are filled in, nothing is overwritten) and it is always safe to retry. 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.

What 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.