specpilot

endpoint

https://init.specpilot.dev/mcp

protocol

streamable-http ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is specpilot live?

Yes — it answered the hub's last check (checked 37m ago). It answered 100% of checks over the last 30 days.

Is specpilot free to use?

Yes — the hub reached it with no key and no payment.

What tools does specpilot have?

2 tools: specpilot_generate_specs, specpilot_next_questions.

Is specpilot safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• specpilot_next_questions reads open 15h ago

  Returns the unanswered SpecPilot onboarding questions of the next incomplete step, gated by the answers so far: questions that do not apply are omitted, and options are filtered, badged or flagged as in the SpecPilot web chat. Stateless: send every answer collected so far on each call. Procedure: (1) Set `isNewBuild` from whether the repo already has real source code. (2) Infer what the repo answers instead of asking: `platforms` from the manifests and layout, `languageOverride`, `ideAgent` (you are the IDE), `handle` from git config or the origin remote, `projectName` from the manifest or folder name, `projectDescription` from the README only if it plainly says what the project is. (3) Call this tool, answer what the repo makes obvious and ask the developer the rest, a whole step per message. Send an empty value for a declined optional question or it is asked again; send `todoSentinel` verbatim when they do not know yet. For `projectDescription`, an exact returned chip label infers `projectCategory` and gates later questions; free prose infers nothing. Confirm pre-seeded values rather than accepting them silently. (4) Loop until `done` is true, then call specpilot_generate_specs and follow its `nextSteps` for where each file goes.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
      "answers": {
        "type": "object",
        "properties": {
          "cicd": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "CI/CD practices - automatically running tests and deploying on every change."
          },
          "handle": {
            "type": "string",
            "description": "The developer GitHub handle. Optional. Infer from git config or the origin remote."
          },
          "uiStyle": {
            "type": "string",
            "description": "Preferred UI style."
          },
          "apiStyle": {
            "type": "string",
            "description": "API style - REST, GraphQL, gRPC or tRPC."
          },
          "figmaUrl": {
            "type": "string",
            "description": "Figma link."
          },
          "ideAgent": {
            "type": "string",
            "description": "The editor or AI IDE in use - claudecode, cursor, copilot, codex, windsurf. You are the IDE, so set this yourself."
          },
          "nonGoals": {
            "type": "string",
            "description": "What this project explicitly will NOT do."
          },
          "teamSize": {
            "type": "string",
            "description": "How many people are building this."
          },
          "databases": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Database kinds in use - SQL, NoSQL, cache/key-value, vector. As many as apply."
          },
          "otherApis": {
            "type": "string",
            "description": "External APIs or services not covered by integrations."
          },
          "platforms": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Platforms this should run on, e.g. web, ios, android, desktop. Infer from the dependency manifests and repo layout."
          },
          "scaleTier": {
            "type": "string",
            "description": "Expected scale of the system."
          },
          "userTypes": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Who is going to use this system, e.g. end users, admins, internal staff."
          },
          "compliance": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Compliance regimes that apply - GDPR, HIPAA, SOC 2. Pick by the actual situation (EU users, health data, payments)."
          },
          "isNewBuild": {
            "type": "boolean",
            "description": "True for a greenfield project, false when adding onto an existing codebase."
          },
          "activeUsers": {
            "type": "string",
            "description": "Roughly how many active users are expected, as a range."
          },
          "designNotes": {
            "type": "string",
            "description": "Notes on the designs."
          },
          "projectName": {
            "type": "string",
            "description": "Short name for the project. Required by specpilot_generate_specs. Infer from the package manifest or the folder name."
          },
          "authStrategy": {
            "type": "string",
            "description": "Auth approach - a protocol built in-house (JWT/OAuth/SAML) or a managed service (Clerk, Auth0, Firebase)."
          },
          "availability": {
            "type": "string",
            "description": "Availability SLA target as a fraction of uptime."
          },
          "designSystem": {
            "type": "string",
            "description": "Design system in use."
          },
          "integrations": {
            "type": "object",
            "description": "Third-party integrations keyed by category, e.g. { payments: [\"stripe\"] }. Only categories relevant to the project type apply.",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {
              "type": "array",
              "items": {
                "type": "string"
              }
            }
          },
          "accessControl": {
            "type": "string",
            "description": "The access control model."
          },
          "buildTimeline": {
            "type": "string",
            "description": "How long the build is expected to take."
          },
          "realtimeTypes": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Realtime transports - WebSockets, SSE, polling. Leave empty when nothing needs to update live."
          },
          "systemPattern": {
            "type": "string",
            "description": "Architecture pattern - monolith, modular monolith, or microservices."
          },
          "customUserType": {
            "type": "string",
            "description": "A user type in free text, when none of the userTypes options fit."
          },
          "localDatabases": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "On-device stores backing offline support. Leave empty when offline is not needed."
          },
          "offlineSupport": {
            "type": "boolean",
            "description": "Whether this has to work offline. Set automatically when localDatabases is non-empty."
          },
          "apiResponseTime": {
            "type": "string",
            "description": "Target API response time."
          },
          "hasDesignAssets": {
            "type": "boolean",
            "description": "Whether Figma files, a design system or mockups exist."
          },
          "projectCategory": {
            "anyOf": [
              {
                "enum": [
                  "saas",
                  "api",
                  "mobile",
                  "cli",
                  "pipeline",
                  "ml",
                  "static",
                  "docs",
                  "extension",
                  "library",
                  "other"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Project archetype. Normally inferred from projectDescription when it exactly matches a returned chip label - send it only if you already know it."
          },
          "realtimeEnabled": {
            "type": "boolean",
            "description": "Whether anything updates live without a refresh. Set automatically when realtimeTypes is non-empty."
          },
          "testingStrategy": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Testing approaches this project will use."
          },
          "dataSyncStrategy": {
            "type": "string",
            "description": "How conflicting local and server state gets reconciled once the device is back online."
          },
          "languageOverride": {
            "type": "string",
            "description": "Primary language, when it should override what SpecPilot infers from the repo."
          },
          "securityConcerns": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Security measures to plan for - encryption, rate limiting, audit logging."
          },
          "deploymentTargets": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Where this ships - cloud hosting, a package registry, a browser store. The option list depends on the project type."
          },
          "accessibilityNotes": {
            "type": "string",
            "description": "Anything further on accessibility or constraints, in free text."
          },
          "projectDescription": {
            "type": "string",
            "description": "One line saying what the project is. Required by specpilot_generate_specs. Sending one of the chip labels returned by specpilot_next_questions verbatim is what infers projectCategory and gates every later question; free prose infers nothing."
          },
          "technicalConstraints": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Hard constraints - budget, existing infrastructure, legacy systems, a fixed deadline."
          },
          "constraintDescription": {
            "type": "string",
            "description": "More detail on whatever was named in technicalConstraints."
          },
          "specialConsiderations": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Cross-cutting concerns that apply, such as accessibility, internationalisation or offline support."
          }
        },
        "description": "Every SpecPilot onboarding answer collected so far. The server is stateless, so resend the whole object on every call; omit it entirely on the first call to get step 1."
      }
    }
  }

  arguments 249 lines copy
• specpilot_generate_specs reads unknown 15h ago

  Generates the complete SpecPilot .specs/ file set plus the matching IDE rules and slash-command files from a full answer set - identical to what the SpecPilot web chat produces for the same answers. Requires projectName and projectDescription. Returns the files to write and the steps to follow after writing them.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "answers"
    ],
    "properties": {
      "answers": {
        "type": "object",
        "properties": {
          "cicd": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "handle": {
            "type": "string"
          },
          "uiStyle": {
            "type": "string"
          },
          "apiStyle": {
            "type": "string"
          },
          "figmaUrl": {
            "type": "string"
          },
          "ideAgent": {
            "type": "string"
          },
          "nonGoals": {
            "type": "string"
          },
          "teamSize": {
            "type": "string"
          },
          "databases": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "otherApis": {
            "type": "string"
          },
          "platforms": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "scaleTier": {
            "type": "string"
          },
          "userTypes": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "compliance": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "isNewBuild": {
            "type": "boolean"
          },
          "activeUsers": {
            "type": "string"
          },
          "designNotes": {
            "type": "string"
          },
          "projectName": {
            "type": "string"
          },
          "authStrategy": {
            "type": "string"
          },
          "availability": {
            "type": "string"
          },
          "designSystem": {
            "type": "string"
          },
          "integrations": {
            "type": "object",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {
              "type": "array",
              "items": {
                "type": "string"
              }
            }
          },
          "accessControl": {
            "type": "string"
          },
          "buildTimeline": {
            "type": "string"
          },
          "realtimeTypes": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "systemPattern": {
            "type": "string"
          },
          "customUserType": {
            "type": "string"
          },
          "localDatabases": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "offlineSupport": {
            "type": "boolean"
          },
          "apiResponseTime": {
            "type": "string"
          },
          "hasDesignAssets": {
            "type": "boolean"
          },
          "projectCategory": {
            "anyOf": [
              {
                "enum": [
                  "saas",
                  "api",
                  "mobile",
                  "cli",
                  "pipeline",
                  "ml",
                  "static",
                  "docs",
                  "extension",
                  "library",
                  "other"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ]
          },
          "realtimeEnabled": {
            "type": "boolean"
          },
          "testingStrategy": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "dataSyncStrategy": {
            "type": "string"
          },
          "languageOverride": {
            "type": "string"
          },
          "securityConcerns": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "deploymentTargets": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "accessibilityNotes": {
            "type": "string"
          },
          "projectDescription": {
            "type": "string"
          },
          "technicalConstraints": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "constraintDescription": {
            "type": "string"
          },
          "specialConsiderations": {
            "type": "array",
            "items": {
              "type": "string"
            }
          }
        },
        "description": "The complete SpecPilot answer set to generate from - everything collected through specpilot_next_questions, whose schema describes each field. projectName and projectDescription are required; every other field falls back to a sensible default."
      }
    }
  }

  arguments 209 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.