{
  "markdown": "# Conducted MCP\n\n**An MCP server that helps an AI agent plan and track a software project the way a disciplined team would — and it was built using the very methodology it ships.**\n\nConducted MCP exposes [Conducted Development](docs/DESIGN_SKETCH.md) — a lightweight, intent-driven methodology — to any MCP-capable agent (Claude Desktop, Cursor, and others). It is a stateless **advisor + validator**: it holds no project data and touches no files or git. The agent does all the I/O; the server supplies judgment — validate this artifact, is a standup due, what's the procedure for this phase, does this decision belong in the log.\n\n> **The differentiator:** this repository's own [`work/`](work/) folder — goal briefs, intent docs, a decision log, and cycle standups — was produced *under the methodology the tool implements*. It is the proof of process, not a sample.\n\n---\n\n## What it does\n\nA connecting agent gets, on demand:\n\n- **A guided kickoff** (`kickoff` prompt + `kickoff_questions` / `kickoff_plan` tools) — a branching Q&A that bootstraps a project's planning structure for greenfield *or* existing codebases. For existing code the agent inspects the repo and the server pre-fills answers so the human confirms rather than authors from scratch.\n- **Strict artifact validation** (`validate_artifact`) — submit a goal brief / intent doc / session log / standup, get back `{ valid, missing, warnings }`.\n- **Phase procedures** (`next_procedure`) — the ordered steps, what to read first, and the escalation points for wherever the agent is in the loop.\n- **Mechanical rule checks** (`standup_due`, `evaluate_gate`, `decision_log_guidance`) — the rituals a solo practitioner most often lets slide, as stateless judgments over supplied facts.\n\nThe methodology's guides, templates, and conventions are served as read-only **resources** (`conducted://guide/*`, `conducted://template/*`, `conducted://conventions`) so an agent can learn the rules in-band.\n\n---\n\n## Why it's built this way (Model C)\n\nThe server **cannot** enforce — an agent always has direct file access. So instead of pretending to be a gatekeeper, it is an advisor: pure functions returning judgments and procedures, no side effects, nothing to host with no data and no auth-to-data. That makes it portable, trivially testable, and cheap to run locally or remotely. The reasoning is written up in [`docs/DESIGN_SKETCH.md`](docs/DESIGN_SKETCH.md) and the resolved trade-offs in [`DECISIONS.md`](DECISIONS.md).\n\n---\n\n## Quick start\n\nPublished on npm as **[`conducted-mcp`](https://www.npmjs.com/package/conducted-mcp)** — runs with zero install via `npx`.\n\nAdd the server to your MCP client. **Claude Desktop** (`claude_desktop_config.json`) or **Cursor** (`.cursor/mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"conducted\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"conducted-mcp\"]\n    }\n  }\n}\n```\n\nThen ask your agent to \"run the Conducted kickoff for this project,\" or call any tool directly.\n\n### Or connect to the hosted endpoint (no install)\n\nA stateless **Streamable HTTP** endpoint runs live on Cloudflare Workers — connect by URL, nothing to install:\n\n```json\n{\n  \"mcpServers\": {\n    \"conducted\": {\n      \"url\": \"https://conducted-mcp.jonathanmostov.workers.dev/mcp\"\n    }\n  }\n}\n```\n\n> Because the server is stateless and holds no data (Model C), the endpoint is safe to run unauthenticated, guarded by rate limiting.\n\n---\n\n## Demo\n\nSee **[`docs/DEMO.md`](docs/DEMO.md)** for a real transcript of the `kickoff` flow — the front-door prompt, the branched interview, and the phase procedures — captured verbatim from the running server. <!-- a client-side screen recording will be added here -->\n\n---\n\n## Development\n\n```bash\nnpm install\nnpm run build     # bundles the methodology text, then strict tsc\nnpm test          # vitest\nnpm run lint      # eslint + prettier\nnpm start         # run the stdio server\n```\n\nThe server is TypeScript on the official [`@modelcontextprotocol/sdk`](https://github.com/modelcontextprotocol), ESM, strict mode. See [`CONTRIBUTING.md`](CONTRIBUTING.md) for the layout and conventions.\n\n---\n\n## The methodology, in the repo\n\n- [`work/goal-briefs/`](work/goal-briefs/) — the goal briefs that drove this build\n- [`work/intent-docs/`](work/intent-docs/) — one per ticket, the per-session contracts\n- [`work/standups/`](work/standups/) — cycle-gate standups\n- [`work/decision-log.md`](work/decision-log.md) — the append-only record of decisions\n- [`AGENT_CONVENTIONS.md`](AGENT_CONVENTIONS.md) — how every session runs, model- and tool-agnostic\n\n---\n\n## License\n\n[MIT](LICENSE) © 2026 Jonathan Mostov\n",
  "bytes": 4612,
  "sha": "cd654075bb1cf6fc91b1af5976339b1c084d49e0038f9e95365bf6a74915eca3",
  "repo_slug": "mostov82/conducted-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_mostov82_conducted_mcp_56b847fd/readme"
}