Koskamo

TORNEO MCP

An evidence layer and MCP server that provides agents with replayable measurements, cost estimates, and uncertainty intervals for AI tools on frozen tasks. It allows agents to query case studies, retrieve run details, and understand limits before recommending tools, ensuring decisions are based on replicated data rather than rankings.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

TORNEO MCP logo, by Tempo AI LLCCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by Tempo AI LLC
MCP endpoint (Streamable HTTP)
https://torneo.ai/api/mcp
Vendor documentation

What its tools do

9 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (9)

9 of 9 have a description · 0 of 9 declare behavior hints · 0 of 8 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Query evidence for specific AI tool categories like email finding or transcription
  • Retrieve detailed results and cost metrics for specific task runs
  • Explain limitations and uncertainty intervals for tool performance data
  • Request or submit needs for new tournament-style evaluations

Source and maintenance

Community listingRegistry 0.1.1
mcp-registry: io.github.devlollc/torneo@0.1.1Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
torneo 0.2.0
MCP protocol negotiated in check
2025-11-25
Tools
9 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

TORNEO is the evidence layer built for agents to consult before recommending an AI agent: replayable measurements per task class, with uncertainty, cost per resolved task, observation date and limits. Tell TORNEO what your user needs; it answers with the applicable evidence and what is missing. Never 'the best tool'. TORNEO evidence layer, operated by Tempo AI LLC. Discover categories, request an advisory need, follow its id, and cite dated canonical evidence with uncertainty and limits. Requests never start runs. Unknown cost is UNKNOWN (null), unknown need state is partial. Fixtures are synthetic, never real measurements. Never name a single best tool.

Tools

9 advertised

list_categories
Advertised by the server during the last successful anonymous check.

Discover categories with dated status and fixture flags. Fixtures are synthetic, never real evidence.

list_categories input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {},
  "additionalProperties": false
}
get_results
Advertised by the server during the last successful anonymous check.

Canonical evidence for a category. Cite observed_at, uncertainty and limits; never the best tool. INSUFFICIENT_EVIDENCE is not a ranking.

get_results input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "category"
  ],
  "properties": {
    "category": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9-]{1,63}$"
    }
  },
  "additionalProperties": false
}
get_run
Advertised by the server during the last successful anonymous check.

Canonical result bundle or explicit PRE_REGISTERED state. Unknown cost is null / UNKNOWN.

get_run input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "run_id"
  ],
  "properties": {
    "run_id": {
      "type": "string",
      "pattern": "^[A-Z0-9][A-Z0-9-]{1,63}$"
    }
  },
  "additionalProperties": false
}
explain_limits
Advertised by the server during the last successful anonymous check.

Limits, freshness, conflicts and answer rule of a category or run. Read before citing evidence.

explain_limits input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "run_id": {
      "type": "string",
      "pattern": "^[A-Z0-9][A-Z0-9-]{1,63}$"
    },
    "category": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9-]{1,63}$"
    }
  },
  "additionalProperties": false
}
get_auto_tournament
Advertised by the server during the last successful anonymous check.

Automatic attempts, including failures: current private-store state when configured, otherwise a published snapshot. No execution is triggered.

get_auto_tournament input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "category"
  ],
  "properties": {
    "run_id": {
      "type": "string",
      "pattern": "^[A-Z0-9][A-Z0-9-]{1,63}$"
    },
    "category": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9-]{1,63}$"
    }
  },
  "additionalProperties": false
}
submit_need
Advertised by the server during the last successful anonymous check.

Log an advisory need.v1 request. Do not include personal or secret data. Returns need-id; persistence is partial until private ingestion and publication.

submit_need input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "need"
  ],
  "properties": {
    "need": {
      "type": "object",
      "required": [
        "schema",
        "requester",
        "task_class"
      ],
      "properties": {
        "schema": {
          "type": "string",
          "const": "need.v1"
        },
        "requester": {
          "type": "object",
          "required": [
            "kind",
            "origin"
          ],
          "properties": {
            "kind": {
              "enum": [
                "agent",
                "buyer",
                "vendor",
                "operator",
                "researcher"
              ],
              "type": "string"
            },
            "origin": {
              "type": "string"
            }
          },
          "additionalProperties": false
        },
        "adaptation": {
          "type": "object",
          "required": [
            "kind"
          ],
          "properties": {
            "kind": {
              "enum": [
                "none",
                "view",
                "next_season",
                "on_demand"
              ],
              "type": "string"
            }
          },
          "additionalProperties": false
        },
        "priorities": {
          "type": "object",
          "properties": {
            "cost": {
              "type": "number",
              "maximum": 1,
              "minimum": 0
            },
            "latency": {
              "type": "number",
              "maximum": 1,
              "minimum": 0
            },
            "quality": {
              "type": "number",
              "maximum": 1,
              "minimum": 0
            },
            "reliability": {
              "type": "number",
              "maximum": 1,
              "minimum": 0
            }
          },
          "additionalProperties": false
        },
        "task_class": {
          "type": "string",
          "pattern": "^[a-z0-9][a-z0-9-]{1,63}$"
        },
        "constraints": {
          "type": "object",
          "properties": {
            "languages": {
              "type": "array",
              "items": {
                "type": "string",
                "pattern": "^[a-z]{2,3}(-[A-Z]{2})?$"
              },
              "maxItems": 10
            },
            "interfaces": {
              "type": "array",
              "items": {
                "enum": [
                  "api",
                  "cli",
                  "mcp"
                ],
                "type": "string"
              },
              "maxItems": 3
            },
            "data_residency": {
              "enum": [
                "any",
                "ch",
                "eu",
                "us"
              ],
              "type": "string"
            },
            "max_latency_ms": {
              "type": "integer",
              "maximum": 9007199254740991,
              "exclusiveMinimum": 0
            },
            "max_cost_per_unit_usd": {
              "type": "number",
              "minimum": 0
            }
          },
          "additionalProperties": false
        },
        "description": {
          "type": "string"
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}
request_tournament
Advertised by the server during the last successful anonymous check.

Request a tournament using need.v1. Advisory only; never starts a run or spends. Follow the returned id with get_need.

request_tournament input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "need"
  ],
  "properties": {
    "need": {
      "type": "object",
      "required": [
        "schema",
        "requester",
        "task_class"
      ],
      "properties": {
        "schema": {
          "type": "string",
          "const": "need.v1"
        },
        "requester": {
          "type": "object",
          "required": [
            "kind",
            "origin"
          ],
          "properties": {
            "kind": {
              "enum": [
                "agent",
                "buyer",
                "vendor",
                "operator",
                "researcher"
              ],
              "type": "string"
            },
            "origin": {
              "type": "string"
            }
          },
          "additionalProperties": false
        },
        "adaptation": {
          "type": "object",
          "required": [
            "kind"
          ],
          "properties": {
            "kind": {
              "enum": [
                "none",
                "view",
                "next_season",
                "on_demand"
              ],
              "type": "string"
            }
          },
          "additionalProperties": false
        },
        "priorities": {
          "type": "object",
          "properties": {
            "cost": {
              "type": "number",
              "maximum": 1,
              "minimum": 0
            },
            "latency": {
              "type": "number",
              "maximum": 1,
              "minimum": 0
            },
            "quality": {
              "type": "number",
              "maximum": 1,
              "minimum": 0
            },
            "reliability": {
              "type": "number",
              "maximum": 1,
              "minimum": 0
            }
          },
          "additionalProperties": false
        },
        "task_class": {
          "type": "string",
          "pattern": "^[a-z0-9][a-z0-9-]{1,63}$"
        },
        "constraints": {
          "type": "object",
          "properties": {
            "languages": {
              "type": "array",
              "items": {
                "type": "string",
                "pattern": "^[a-z]{2,3}(-[A-Z]{2})?$"
              },
              "maxItems": 10
            },
            "interfaces": {
              "type": "array",
              "items": {
                "enum": [
                  "api",
                  "cli",
                  "mcp"
                ],
                "type": "string"
              },
              "maxItems": 3
            },
            "data_residency": {
              "enum": [
                "any",
                "ch",
                "eu",
                "us"
              ],
              "type": "string"
            },
            "max_latency_ms": {
              "type": "integer",
              "maximum": 9007199254740991,
              "exclusiveMinimum": 0
            },
            "max_cost_per_unit_usd": {
              "type": "number",
              "minimum": 0
            }
          },
          "additionalProperties": false
        },
        "description": {
          "type": "string"
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}
get_need
Advertised by the server during the last successful anonymous check.

Follow need-id in current private-store state when configured, otherwise the published snapshot. Unknown or unavailable means partial, not refused.

get_need input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "need_id"
  ],
  "properties": {
    "need_id": {
      "type": "string",
      "pattern": "^need-[0-9a-f]{16}$"
    }
  },
  "additionalProperties": false
}
decide
Advertised by the server during the last successful anonymous check.

Read-only decision.v1 for one category and a declared context: constraint applicability first, then EVIDENCE or ABSTAIN with a stable reason_code (answer_rule.v3). An abstention removes the verdict only; evidence, reservations and gaps stay. Never a rank on overlapping intervals. Replay and attestation verdicts are as of the last build.

decide input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "category"
  ],
  "properties": {
    "as_of": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}Z$"
    },
    "category": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9-]{1,63}$"
    },
    "constraints": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {
        "type": [
          "string",
          "number",
          "boolean"
        ]
      }
    },
    "max_age_days": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": 0
    }
  },
  "additionalProperties": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (3 of 3 answered).

  1. 2026-11-06: 1 of 1 checks answered
  2. 2026-11-07: 2 of 2 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
663 ms
95th percentile latency
663 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 663 ms · metadata changed · 9 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http torneo-mcp https://torneo.ai/api/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add torneo-mcp --url https://torneo.ai/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable torneo-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "torneo-mcp": {
      "url": "https://torneo.ai/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "torneo-mcp": {
      "type": "streamableHttp",
      "url": "https://torneo.ai/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start torneo-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "torneo-mcp": {
      "type": "http",
      "url": "https://torneo.ai/api/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http torneo-mcp https://torneo.ai/api/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://torneo.ai/api/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "torneo-mcp": {
      "serverUrl": "https://torneo.ai/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like TORNEO MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 5,681