Server definition

Hash: sha256:9fe6df7ad0b9237a2e16f2fa7d843e3927f65509a7874cfd916255089d11add4
What it is: What a remote MCP server returned when asked what it offers: 9 tools

The blob, as servednamed by its sha256

{
  "instructions": "Use this server for three categories of work. Category 1 — Agent tuning: Call recommend_agent_configuration when designing, tuning, or diagnosing an AI agent. Category 2 — Translation: Call interpret when a user says something ambiguous. Call normalize when input is fragmented. Call rewrite when text needs tone adjustment. Category 3 — Translation Bridge (per-user adaptation): Call calibrate_profile once to build the user’s ReceiverProfile from five quick questions (store the returned JSON in the user’s notes/memory for reuse). Then, on EVERY reply to that user, call render_reply with your draft and their profile, and apply the returned instructions before answering. When the user’s request is ambiguous, call prepare_prompt with their text and profile to recover intent before acting. This is the loop: prepare_prompt on the way in, render_reply on the way out. When the user’s request could mean several different things, call route_intent — and YOU propose the candidate readings: 3–7 short hypotheses covering the plausible interpretations of THIS message (including likely-typo readings and idiom-vs-literal readings), with your own likelihood estimates. The built-in default set is a generic product-intent starter, not an interpretation engine — passing it for arbitrary sentences yields uniform confusion over irrelevant options. Division of labor: the model GENERATES the branches; the deterministic router HOLDS them, scores the ambiguity, and decides commit / present options / clarify. route_intent is the AUTHORITY on commit-vs-clarify; prepare_prompt supplies the canonical translation and recovered entities — when the two disagree on whether to ask, follow route_intent.",
  "tools": [
    {
      "description": "Build a ReceiverProfile (TI, SG, FT, UE, AR — continuous 0-100, never a category label) from five behavioral forced-choice answers. Call with NO answers to get the five questions to ask the user; call again with their answers (a/b/c per primitive) to get the profile. Store the returned profile JSON in the user’s notes or memory and pass it to render_reply / prepare_prompt on every turn. Deterministic and stateless — nothing is stored server-side. Schema: https://rpcs1.dev/v1/receiver-profile.json",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "answers": {
            "additionalProperties": false,
            "description": "Chosen option id per primitive. Omit entirely to receive the questions.",
            "properties": {
              "AR": {
                "enum": [
                  "a",
                  "b",
                  "c"
                ],
                "type": "string"
              },
              "FT": {
                "enum": [
                  "a",
                  "b",
                  "c"
                ],
                "type": "string"
              },
              "SG": {
                "enum": [
                  "a",
                  "b",
                  "c"
                ],
                "type": "string"
              },
              "TI": {
                "enum": [
                  "a",
                  "b",
                  "c"
                ],
                "type": "string"
              },
              "UE": {
                "enum": [
                  "a",
                  "b",
                  "c"
                ],
                "type": "string"
              }
            },
            "type": "object"
          }
        },
        "type": "object"
      },
      "name": "calibrate_profile",
      "outputSchema": null
    },
    {
      "description": "The calibrated ambiguity surface: deterministic structural fork detectors (reference, scope, grouping, compare-vs-choose, polysemy) with character-offset spans, plus per-reading one-line clarifiers the sender can append to lock a reading in. Returns competing readings, an ask-back question, and a forked-answer scaffold. Silent on clean text by contract. Runs the deterministic mirror floor only over MCP (no model). Prefer this over interpret for span-level ambiguity detection: interpret’s entity list is a word-list engine (calibrated 2026-08-15: no discrimination on conversational text) — advisory only.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "rejected": {
            "description": "Reading summaries the user already rejected — never re-offered.",
            "items": {
              "type": "string"
            },
            "maxItems": 12,
            "type": "array"
          },
          "text": {
            "description": "The message to analyze for forks.",
            "maxLength": 5000,
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "fork",
      "outputSchema": null
    },
    {
      "description": "Detect ambiguity in user messages using the RPCS-1 Signature Ambiguity Framework. Returns AR level (AR0-AR5), confidence, candidate interpretations with scores, clarifying questions, and suggested next step. Use when a user says something vague, passive-aggressive, or underspecified.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "risk": {
            "default": "advice",
            "description": "Risk category for ambiguity threshold.",
            "enum": [
              "casual",
              "advice",
              "high-stakes",
              "safety-critical"
            ],
            "type": "string"
          },
          "text": {
            "description": "The message to interpret.",
            "maxLength": 5000,
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "interpret",
      "outputSchema": null
    },
    {
      "description": "Clean up text with ellipses, fragments, and run-on thoughts into coherent prose. Use when a user types stream-of-consciousness or fragmented input.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "text": {
            "description": "Fragmented text to normalize.",
            "maxLength": 5000,
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "normalize",
      "outputSchema": null
    },
    {
      "description": "The inbound half of the Translation Bridge loop. Takes the user’s raw message (possibly ambiguous, fragmented, or underspecified) plus their ReceiverProfile, and returns the recovered intent, a canonical translation to act on, ambiguity level, and — profile-aware — whether to clarify or commit. Call this before acting on any ambiguous user request. Scope note: its detectors are lexical/structural (vague signals, ambiguous references) — for the commit-vs-clarify DECISION, route_intent (with your own proposed readings) is the authority; when they disagree, follow route_intent.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "profile": {
            "additionalProperties": false,
            "description": "The user’s ReceiverProfile from calibrate_profile. Shapes clarify-vs-commit behavior.",
            "properties": {
              "AR": {
                "description": "Ambiguity Resolution: 100 = commit to best reading, 0 = clarify first",
                "maximum": 100,
                "minimum": 0,
                "type": "number"
              },
              "FT": {
                "description": "Filtering Threshold: 100 = explicit and literal, 0 = subtext lands",
                "maximum": 100,
                "minimum": 0,
                "type": "number"
              },
              "SG": {
                "description": "Signal Gain: 0 = flat and factual, 100 = warm and expressive",
                "maximum": 100,
                "minimum": 0,
                "type": "number"
              },
              "TI": {
                "description": "Temporal Integration: 0 = bottom line first, 100 = full context first",
                "maximum": 100,
                "minimum": 0,
                "type": "number"
              },
              "UE": {
                "description": "Update Elasticity: 100 = pushback welcome, 0 = prefers consistency",
                "maximum": 100,
                "minimum": 0,
                "type": "number"
              }
            },
            "required": [
              "TI",
              "SG",
              "FT",
              "UE",
              "AR"
            ],
            "type": "object"
          },
          "risk": {
            "default": "advice",
            "description": "Risk category for the ambiguity threshold.",
            "enum": [
              "casual",
              "advice",
              "high-stakes",
              "safety-critical"
            ],
            "type": "string"
          },
          "text": {
            "description": "The user’s raw message.",
            "maxLength": 5000,
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "prepare_prompt",
      "outputSchema": null
    },
    {
      "description": "Diagnose why a deployed AI agent may fail. Takes environmental entropy, predictability, stakes, context horizon, and commitment style, then returns receiver profile values (TI, SG, FT, UE, AR), platform parameters (temperature, top_p, strategy), regime prediction, reasoning, and warnings. Optionally pass target_model (the actual model id) to attach MEASURED per-model receiver posture (E-LIT table): evidence-graded literalness, truth-override boundary, and translation directives. Deterministic, stateless, read-only — does not store past recommendations.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "environment": {
            "additionalProperties": false,
            "default": {
              "commitment_style": "cautious",
              "context_relevance": "medium",
              "entropy": "dynamic",
              "predictability": "somewhat_predictable",
              "stakes": "high"
            },
            "properties": {
              "commitment_style": {
                "default": "cautious",
                "description": "How quickly the agent should commit to an action.",
                "enum": [
                  "decisive",
                  "balanced",
                  "cautious"
                ],
                "type": "string"
              },
              "context_relevance": {
                "default": "medium",
                "description": "How far back relevant context usually extends.",
                "enum": [
                  "short",
                  "medium",
                  "long"
                ],
                "type": "string"
              },
              "entropy": {
                "default": "dynamic",
                "description": "How often the operating environment changes.",
                "enum": [
                  "stable",
                  "moderate",
                  "dynamic",
                  "chaotic"
                ],
                "type": "string"
              },
              "predictability": {
                "default": "somewhat_predictable",
                "description": "How predictable changes are when they occur.",
                "enum": [
                  "highly_predictable",
                  "somewhat_predictable",
                  "unpredictable"
                ],
                "type": "string"
              },
              "stakes": {
                "default": "high",
                "description": "The cost of an incorrect agent action.",
                "enum": [
                  "low",
                  "medium",
                  "high",
                  "catastrophic"
                ],
                "type": "string"
              }
            },
            "type": "object"
          },
          "target_model": {
            "description": "Optional: the actual model id this agent will run on (e.g. \"claude-sonnet-4-6\", \"deepseek-v4-pro\"). When it matches a measured per-model receiver entry (E-LIT table), measured translation directives and evidence-graded posture data are attached to platform_parameters. Unknown models fall back to platform-level behavior unchanged.",
            "maxLength": 200,
            "minLength": 1,
            "type": "string"
          },
          "target_platform": {
            "default": "anthropic",
            "description": "The platform whose runtime parameters should be recommended.",
            "enum": [
              "anthropic",
              "openai",
              "open_source",
              "generic"
            ],
            "type": "string"
          },
          "task": {
            "additionalProperties": false,
            "default": {
              "domain": "customer_support",
              "expected_duration_per_call": "medium",
              "task_summary": "Customer support agent handling refunds, billing disputes, and policy exceptions"
            },
            "properties": {
              "domain": {
                "default": "customer_support",
                "description": "Optional domain such as coding, research, or support.",
                "maxLength": 100,
                "minLength": 1,
                "type": "string"
              },
              "expected_duration_per_call": {
                "default": "medium",
                "enum": [
                  "short",
                  "medium",
                  "long"
                ],
                "type": "string"
              },
              "task_summary": {
                "default": "Customer support agent handling refunds, billing disputes, and policy exceptions",
                "description": "Plain-language description of what the AI agent does.",
                "maxLength": 2000,
                "minLength": 1,
                "type": "string"
              }
            },
            "type": "object"
          }
        },
        "type": "object"
      },
      "name": "recommend_agent_configuration",
      "outputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "confidence": {
            "enum": [
              "high",
              "medium",
              "low"
            ],
            "type": "string"
          },
          "imm_principles_applied": {
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "platform_parameters": {
            "additionalProperties": false,
            "properties": {
              "context_strategy": {
                "enum": [
                  "long_window",
                  "rolling_summary",
                  "frequent_grounding"
                ],
                "type": "string"
              },
              "max_tokens": {
                "type": "number"
              },
              "model_recommendation": {
                "type": "string"
              },
              "receiver_evidence": {
                "additionalProperties": false,
                "description": "Present only when target_model has a measured per-model receiver entry.",
                "properties": {
                  "cb": {
                    "description": "E-LIT-3 care boundary (1-4): highest emotional-intensity rung at which fenced answers stay bare.",
                    "type": "number"
                  },
                  "display_name": {
                    "type": "string"
                  },
                  "fringe": {
                    "description": "Rungs with modal comply-then-correct.",
                    "items": {
                      "type": "number"
                    },
                    "type": "array"
                  },
                  "grade": {
                    "description": "Evidence grade of the measurement — travels with the data.",
                    "enum": [
                      "confirmatory",
                      "corroboration",
                      "self_measurement"
                    ],
                    "type": "string"
                  },
                  "li2": {
                    "description": "Fenced literalness, [-1, +1].",
                    "type": "number"
                  },
                  "measured_on": {
                    "type": "string"
                  },
                  "model_key": {
                    "type": "string"
                  },
                  "ob": {
                    "description": "Truth-override boundary rung (0-5).",
                    "type": "number"
                  },
                  "sb": {
                    "description": "E-LIT-3 stakes boundary (1-5): highest stakes rung at which format fences still hold. Separate instrument; never pooled with li2/ob.",
                    "type": "number"
                  },
                  "scope": {
                    "type": "string"
                  }
                },
                "required": [
                  "model_key",
                  "display_name",
                  "grade",
                  "li2",
                  "ob",
                  "fringe",
                  "measured_on",
                  "scope"
                ],
                "type": "object"
              },
              "receiver_traits": {
                "description": "Reliability warnings and named traits for the measured receiver.",
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              "retry_strategy": {
                "enum": [
                  "aggressive",
                  "moderate",
                  "minimal"
                ],
                "type": "string"
              },
              "system_prompt_additions": {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              "temperature": {
                "type": "number"
              },
              "tool_use_strategy": {
                "enum": [
                  "explicit_confirmation",
                  "cautious_chaining",
                  "aggressive",
                  "fail_fast"
                ],
                "type": "string"
              },
              "top_p": {
                "type": "number"
              },
              "translation_notes": {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              "translation_posture": {
                "enum": [
                  "direct",
                  "bridging",
                  "face_preserving",
                  "minimal_clarifying"
                ],
                "type": "string"
              }
            },
            "required": [
              "temperature",
              "max_tokens"
            ],
            "type": "object"
          },
          "predicted_regime": {
            "enum": [
              "stable",
              "near_oscillation",
              "near_overload",
              "near_freeze"
            ],
            "type": "string"
          },
          "reasoning": {
            "type": "string"
          },
          "receiver_profile": {
            "additionalProperties": false,
            "properties": {
              "AR": {
                "type": "number"
              },
              "FT": {
                "type": "number"
              },
              "SG": {
                "type": "number"
              },
              "TI": {
                "type": "number"
              },
              "UE": {
                "type": "number"
              }
            },
            "required": [
              "TI",
              "SG",
              "FT",
              "UE",
              "AR"
            ],
            "type": "object"
          },
          "warnings": {
            "items": {
              "type": "string"
            },
            "type": "array"
          }
        },
        "required": [
          "receiver_profile",
          "platform_parameters",
          "predicted_regime",
          "reasoning",
          "warnings",
          "imm_principles_applied",
          "confidence"
        ],
        "type": "object"
      }
    },
    {
      "description": "The outbound half of the Translation Bridge loop. Takes your draft reply plus the user’s ReceiverProfile and returns deterministic rendering instructions (structure, warmth, explicitness, revision posture, ambiguity handling — each with a why-trace). Apply the instructions to your draft before answering. Call this on every reply to a calibrated user.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "profile": {
            "additionalProperties": false,
            "description": "The user’s ReceiverProfile from calibrate_profile.",
            "properties": {
              "AR": {
                "description": "Ambiguity Resolution: 100 = commit to best reading, 0 = clarify first",
                "maximum": 100,
                "minimum": 0,
                "type": "number"
              },
              "FT": {
                "description": "Filtering Threshold: 100 = explicit and literal, 0 = subtext lands",
                "maximum": 100,
                "minimum": 0,
                "type": "number"
              },
              "SG": {
                "description": "Signal Gain: 0 = flat and factual, 100 = warm and expressive",
                "maximum": 100,
                "minimum": 0,
                "type": "number"
              },
              "TI": {
                "description": "Temporal Integration: 0 = bottom line first, 100 = full context first",
                "maximum": 100,
                "minimum": 0,
                "type": "number"
              },
              "UE": {
                "description": "Update Elasticity: 100 = pushback welcome, 0 = prefers consistency",
                "maximum": 100,
                "minimum": 0,
                "type": "number"
              }
            },
            "required": [
              "TI",
              "SG",
              "FT",
              "UE",
              "AR"
            ],
            "type": "object"
          },
          "text": {
            "description": "Your draft reply.",
            "maxLength": 10000,
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "text",
          "profile"
        ],
        "type": "object"
      },
      "name": "render_reply",
      "outputSchema": null
    },
    {
      "description": "Get rewrite instructions for adapting text to a specific style: technical, plain, socially_gentle, concise, detailed, or direct. Use when communication needs tone adjustment.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "style": {
            "default": "plain",
            "description": "Target audience style.",
            "enum": [
              "technical",
              "plain",
              "socially_gentle",
              "concise",
              "detailed",
              "direct"
            ],
            "type": "string"
          },
          "text": {
            "description": "Text to rewrite.",
            "maxLength": 5000,
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "rewrite",
      "outputSchema": null
    },
    {
      "description": "Entropy routing over competing interpretations — the model proposes, the deterministic core disposes. YOU generate the candidate readings of the user’s message (3–7 short hypotheses covering the plausible interpretations, INCLUDING likely-typo readings, idiom-vs-literal readings, and domain senses) and pass them as hypotheses, ideally with your own likelihoods (0–1 per reading) AND a paraphrase per reading — the user’s message rewritten unambiguously under that interpretation, so the user can VERIFY intent by recognition before anything commits (one misread prompt skews a whole thread). The router computes the posterior and its normalized entropy T̂ and returns the decision: commit (one reading dominates), commit_with_note (close alternative disclosed), present_options (several readings live), or clarify (ask before acting — open-endedly when nothing discriminates). Thresholds adapt to the user’s ReceiverProfile (AR widens/narrows the commit region; high FT discloses near-ties). This tool is the commit-vs-clarify AUTHORITY in the pipeline. Omitting hypotheses falls back to a generic six-intent PRODUCT-ROUTING starter set — do not use the fallback for interpreting arbitrary sentences. Deterministic, stateless, read-only. Benchmarked: RTEB v1.1 (developer-bench grade; see docs/routing.md).",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "hypotheses": {
            "description": "Candidate interpretations. Omit to use a generic six-intent starter set plus a catch-all.",
            "items": {
              "additionalProperties": false,
              "properties": {
                "cues": {
                  "description": "Lexical cues for the built-in scorer; omit when passing likelihoods.",
                  "items": {
                    "maxLength": 64,
                    "minLength": 1,
                    "type": "string"
                  },
                  "maxItems": 32,
                  "type": "array"
                },
                "id": {
                  "maxLength": 64,
                  "minLength": 1,
                  "type": "string"
                },
                "label": {
                  "maxLength": 200,
                  "minLength": 1,
                  "type": "string"
                },
                "paraphrase": {
                  "description": "The user’s message REWRITTEN UNAMBIGUOUSLY under this reading. Strongly recommended: when the router asks, the user verifies intent by reading these restatements, not by decoding labels.",
                  "maxLength": 500,
                  "minLength": 1,
                  "type": "string"
                },
                "prior": {
                  "exclusiveMinimum": 0,
                  "type": "number"
                }
              },
              "required": [
                "id",
                "label"
              ],
              "type": "object"
            },
            "maxItems": 24,
            "minItems": 2,
            "type": "array"
          },
          "likelihoods": {
            "additionalProperties": {
              "minimum": 0,
              "type": "number"
            },
            "description": "Optional externally computed likelihood per hypothesis id (e.g. model-derived) — replaces the lexical scorer.",
            "type": "object"
          },
          "profile": {
            "additionalProperties": false,
            "description": "The user’s ReceiverProfile from calibrate_profile. Shapes commit-vs-clarify thresholds.",
            "properties": {
              "AR": {
                "description": "Ambiguity Resolution: 100 = commit to best reading, 0 = clarify first",
                "maximum": 100,
                "minimum": 0,
                "type": "number"
              },
              "FT": {
                "description": "Filtering Threshold: 100 = explicit and literal, 0 = subtext lands",
                "maximum": 100,
                "minimum": 0,
                "type": "number"
              },
              "SG": {
                "description": "Signal Gain: 0 = flat and factual, 100 = warm and expressive",
                "maximum": 100,
                "minimum": 0,
                "type": "number"
              },
              "TI": {
                "description": "Temporal Integration: 0 = bottom line first, 100 = full context first",
                "maximum": 100,
                "minimum": 0,
                "type": "number"
              },
              "UE": {
                "description": "Update Elasticity: 100 = pushback welcome, 0 = prefers consistency",
                "maximum": 100,
                "minimum": 0,
                "type": "number"
              }
            },
            "required": [
              "TI",
              "SG",
              "FT",
              "UE",
              "AR"
            ],
            "type": "object"
          },
          "text": {
            "description": "The user’s raw message.",
            "maxLength": 5000,
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "route_intent",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:9fe6df7ad0b9237a2e16f2fa7d843e3927f65509a7874cfd916255089d11add4 | sha256sum