# Conducted MCP MCP server

Stateless advisor + validator for Conducted Development: kickoff, artifact validation, rule checks.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-mostov82-conducted-mcp
- Repository: https://github.com/Mostov82/conducted-mcp

## Install
- Command: `npx -y conducted-mcp`
- Endpoint: https://conducted-mcp.jonathanmostov.workers.dev/mcp
- Auth: Not captured

## Setup notes
- Package: Npm conducted-mcp v0.1.1
- Remote endpoint: https://conducted-mcp.jonathanmostov.workers.dev/mcp

## Tools
- validate_artifact (Validate a methodology artifact) - Strictly check whether a Conducted Development artifact's text satisfies the methodology's required structure. Supply the artifact's type and its full text (the server never reads files). Returns { valid, missing, warnings }: `missing` lists required sections that are absent, empty, or contain only unmodified template placeholder text (blocking); `warnings` lists sections that are present but look thin (advisory, non-blocking). `valid` is true iff `missing` is empty. Endpoint: https://conducted-mcp.jonathanmostov.workers.dev/mcp
- kickoff_questions (Get the kickoff interview question set) - Return the branched kickoff interview (DECISIONS.md D3/D4). Supply `project_type`: 'greenfield' asks the full set; 'brownfield' uses the agent-supplied `detected` facts (language, framework, tests, CI, existing docs) to pre-fill candidates and drop fully-inferable questions — except LOCKED_DOCS, which is always asked because it is human judgment. Returns { project_type, questions, inferred, notes }; the server reads no files. Endpoint: https://conducted-mcp.jonathanmostov.workers.dev/mcp
- kickoff_plan (Assemble the kickoff file plan) - Assemble, from the bundled templates, the four `_template.md` copies (front-matter tokens replaced), `decision-log.md`, and a filled `AGENT_CONVENTIONS.md` (kickoff guide Steps 2–5). Supply `project_type`, the interview `answers`, optional `detected` (brownfield pre-fill fallback), and optional `existing` (the agent's inventory of files already present). Returns { files: [{ path, content, action }], missing, open_questions, warnings }. The plan is ready iff `missing` is empty (D5 strict); a file with any unresolved {{…}} token is reported in `missing`. Idempotent: already-present files are 'review'/'skip', never overwritten. The server returns content + paths only — it writes nothing (Model C, D2/D6). Endpoint: https://conducted-mcp.jonathanmostov.workers.dev/mcp
- next_procedure (Get the procedure for a methodology phase) - Return the ordered procedure for where the agent is in the methodology loop. Supply `phase` (one of: kickoff, goal_brief, intent_doc, session_open, session_active, session_close, standup) and optional `facts` (e.g. a ticket id) to tailor the output. Returns { steps, reads_first, escalation_points, notes? } sourced from the bundled guides and conventions — the procedure half of advisor + validator. The server reads no files. Endpoint: https://conducted-mcp.jonathanmostov.workers.dev/mcp
- standup_due (Judge whether a standup is due) - Given agent-supplied facts, decide whether a standup is due. Triggers in priority order: a deliverable gate reached → 'gate'; else a dependency intersection → 'intersection'; else more than five working days since the last standup → 'weekly'; else 'none'. Working days are an input (the working week varies by team), never computed from a calendar. Returns { due, reason, detail }. Endpoint: https://conducted-mcp.jonathanmostov.workers.dev/mcp
- evaluate_gate (Evaluate whether a goal brief's gates are resolved) - Encode the goal-brief rule that no session may begin while any gate is open. Supply either a structured `gates` list ([{ id, resolved }]) or a goal-brief `content` string, in which case the GATE LIST checkboxes (- [ ] / - [x]) are parsed. Returns { all_resolved, unresolved, may_begin } where may_begin === all_resolved. The server reads no files — the content is agent-supplied. Endpoint: https://conducted-mcp.jonathanmostov.workers.dev/mcp
- decision_log_guidance (Judge whether a situation belongs in the Decision Log) - Encode the Decision-Log 'when to use it' rules. Set whichever apply: `escalation_fired`, `gate_resolved_cross_cutting`, `affects_multiple_tickets`, `override_architectural`, `confined_to_one_session`. Returns { should_log, reason, entry_template? }; when should_log is true the Context/Trigger/Decision/Rationale/Affects skeleton is returned. A decision confined to one session does not need an entry — the session notes suffice. Endpoint: https://conducted-mcp.jonathanmostov.workers.dev/mcp

## Resources
- conducted://guide/kickoff - Guide: Kickoff How to bootstrap a project under the Conducted Development methodology. MIME type: text/markdown
- conducted://guide/goal-brief - Guide: Goal Brief How to author a Goal Brief (business goal → intent → DoD → gates → decomposition). MIME type: text/markdown
- conducted://guide/intent-doc - Guide: Intent Document How to author an intent document (the per-ticket contract). MIME type: text/markdown
- conducted://guide/session - Guide: Session How to run and log a working session under the methodology. MIME type: text/markdown
- conducted://guide/standup - Guide: Standup How and when to run a standup (the ritual that lets the methodology learn). MIME type: text/markdown
- conducted://template/goal-brief - Template: Goal Brief Fill-in template for a Goal Brief. MIME type: text/markdown
- conducted://template/intent-doc - Template: Intent Document Fill-in template for an intent document. MIME type: text/markdown
- conducted://template/session-log - Template: Session Log Fill-in template for a session log. MIME type: text/markdown
- conducted://template/standup - Template: Standup Fill-in template for a standup. MIME type: text/markdown
- conducted://template/decision-log - Template: Decision Log Fill-in template for the append-only decision log. MIME type: text/markdown
- conducted://template/agent-conventions - Template: Agent Conventions Fill-in template for a project's AGENT_CONVENTIONS.md. MIME type: text/markdown
- conducted://conventions - Conducted MCP — Agent Conventions This project's filled-in AGENT_CONVENTIONS.md. MIME type: text/markdown

## Prompts
- kickoff - Guided project kickoff Walk the connecting agent through bootstrapping a project's Conducted planning structure: read/inspect the project (greenfield vs brownfield), call kickoff_questions, interview the human, call kickoff_plan, write the files, then verify (no stray {{ tokens) and surface the human-judgment items. The server advises; the agent does all I/O (Model C). Arguments: project_path

## Metadata
- Owner: io.github.Mostov82
- Version: 0.1.1
- Runtime: Npm
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 1, 2026
- Source: https://registry.modelcontextprotocol.io