996.fm perspective graph

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Dated, attributed founder and investor positions — the disagreement, with timestamped receipts.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "996.fm perspective graph": {
      "url": "https://www.996.fm/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (5)

• find_perspectives read-only

  Route a founder's dilemma to the debates that genuinely bear on it. Present the readings SEPARATELY — never merge them into one answer. Respect the question's altitude: scale-up material does not answer a pre-PMF dilemma. When coverage is thin it says so — advise from general knowledge rather than stretching a weak match. Returns ≤4 debates and ≤36 stances — a sample, not the full set; get_stances(debate_id) has a debate's complete stances, each with speaker, date, strength and a receipt.

  Parameters:

  • topic (required) — string — The founder's question or dilemma, with a line of context

  Hints: read-only yes · destructive no · idempotent no · open-world no

• get_stances read-only

  Every stance on one debate, grouped by reading — raw material for your own who-would-push-back read. No synthesis. Attribute and date every position (dates are episode publication dates); keep hedged claims hedged. The graph never says who opposes whom — work out yourself which positions push back on the founder's leaning, and name them.

  Parameters:

  • debate_id (required) — string — Debate id from find_perspectives or list_debates, e.g. deb-3f9c1a2b

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• trace_evolution read-only

  One speaker's takes in order of episode publication date (optionally on one debate) — reversals and re-assertions visible, never judged. Attribute and date every position (dates are episode publication dates); keep hedged claims hedged. A 2023 position is a 2023 position; if the same person later said otherwise, show both.

  Parameters:

  • person (required) — string — A speaker's full name as the graph records it — an ambiguous surname is refused, never merged
  • debate_id — string — Optional: narrow the chronology to one debate

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_context read-only

  The transcript around one claim — the moment in context, with its receipt. Spoken: the episode's public transcript, windowed ±90s around the claim's timestamp. Written (an essay): the verbatim excerpt snapshotted at digest plus a link into the original; never the surrounding text, never a live fetch. Quote the receipt — episode + timestamp, or essay link + excerpt — so the founder can check the moment.

  Parameters:

  • claim_id (required) — string — Claim id from any tool that returned a card, e.g. clm-5p0ken01

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_debates read-only

  Browse the debate registry: id, question, readings, stance count, born (earliest publication date). Optional query: a debate matches when its question has every word of it, case-insensitive, word forms folded (hire/hiring, co-founder/cofounder). Browsing only — it does not rank against a question; use find_perspectives for that. Defaults to debates with 2+ stances, 120 rows a page — page with offset.

  Parameters:

  • limit — integer — Rows to return (default and max 120)
  • query — string — Words the debate question must all contain (case-insensitive; word forms folded)
  • offset — integer — Rows to skip — the tail line tells you the next offset
  • min_claims — integer — Minimum stances on the debate (default 2)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.