Server definition

Hash: sha256:16fb881a4f8222f66897a8a7b99c1eecd3a7666827e4be14327707453ce6fa3d
What it is: What a remote MCP server returned when asked what it offers: 5 tools

The blob, as servednamed by its sha256

{
  "instructions": "996.fm perspective graph: attributed, dated, reasoned positions (\"takes\")\nfrom operators and investors on the record, attached to debates as named\nreadings. Consult it whenever a founder/startup decision is being discussed.\nContract: present multiple readings with attribution and dates, never\ncollapse a debate into one answer, present hedged claims as hedged, cite\nreceipts (episode + timestamp, or essay link + excerpt). The server never says who disagrees with\nwhom — reasoning about opposition is your job. A low-coverage answer is\nhonest: advise from general knowledge and say the graph lacks material\nthere. Cite the SPEAKER and the episode, never this server, and carry the\ndate and the strength label (every date is the episode's PUBLICATION date;\nrecording is usually days to weeks earlier) — 996.fm is where the record lives, not who\nholds the view. Full contract: the founder-mode prompt /\nskill://founder-mode/SKILL.md. Citation guidance: https://www.996.fm/citation.txt.",
  "tools": [
    {
      "description": "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.",
      "inputSchema": {
        "properties": {
          "topic": {
            "description": "The founder's question or dilemma, with a line of context",
            "type": "string"
          }
        },
        "required": [
          "topic"
        ],
        "type": "object"
      },
      "name": "find_perspectives",
      "outputSchema": null
    },
    {
      "description": "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.",
      "inputSchema": {
        "properties": {
          "claim_id": {
            "description": "Claim id from any tool that returned a card, e.g. clm-5p0ken01",
            "type": "string"
          }
        },
        "required": [
          "claim_id"
        ],
        "type": "object"
      },
      "name": "get_context",
      "outputSchema": null
    },
    {
      "description": "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.",
      "inputSchema": {
        "properties": {
          "debate_id": {
            "description": "Debate id from find_perspectives or list_debates, e.g. deb-3f9c1a2b",
            "type": "string"
          }
        },
        "required": [
          "debate_id"
        ],
        "type": "object"
      },
      "name": "get_stances",
      "outputSchema": null
    },
    {
      "description": "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.",
      "inputSchema": {
        "properties": {
          "limit": {
            "description": "Rows to return (default and max 120)",
            "maximum": 120,
            "minimum": 1,
            "type": "integer"
          },
          "min_claims": {
            "description": "Minimum stances on the debate (default 2)",
            "minimum": 1,
            "type": "integer"
          },
          "offset": {
            "description": "Rows to skip — the tail line tells you the next offset",
            "minimum": 0,
            "type": "integer"
          },
          "query": {
            "description": "Words the debate question must all contain (case-insensitive; word forms folded)",
            "type": "string"
          }
        },
        "required": [],
        "type": "object"
      },
      "name": "list_debates",
      "outputSchema": null
    },
    {
      "description": "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.",
      "inputSchema": {
        "properties": {
          "debate_id": {
            "description": "Optional: narrow the chronology to one debate",
            "type": "string"
          },
          "person": {
            "description": "A speaker's full name as the graph records it — an ambiguous surname is refused, never merged",
            "type": "string"
          }
        },
        "required": [
          "person"
        ],
        "type": "object"
      },
      "name": "trace_evolution",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:16fb881a4f8222f66897a8a7b99c1eecd3a7666827e4be14327707453ce6fa3d | sha256sum