Aidemd

MCP server that brings intent-driven development to any AI-powered IDE. Manage.aidespec files that live next to your code — the domain context that architects plan from, implementors build from, and QA validates against.

- Project-wide spec discoverywith a progressive disclosure tree that surfaces intent, research, and QA specs at every level of your codebase
- One-command project bootstrapviaaide_init— wires methodology docs, pipeline commands, and this MCP server into your project in a single guided flow
- Automatic naming convention enforcement—aide_scaffoldhandles the.aide/intent.aiderename rules so you never create conflicting specs
- Health-check validationviaaide_validate— detects orphaned specs, missing descriptions, broken links, and naming conflicts before they cause drift
- Code introspectionviaaide_inspect— returns JSDoc, signatures, and kind for named symbols without opening files, giving agents Tier 2 progressive disclosure for code
- Upgrade drift detectionviaaide_upgrade— compares your project's AIDE methodology artifacts against canonical versions and writes updates per-category
- Runtime brain entry-pointviaaide_brain— on-demand tool that returns ready-to-execute prose telling the agent which MCP tools to call and how to reach whatever brain backend is wired, without the agent knowing which backend it is

The fastest path is a single npx command that wires everything up automatically:

- Merges the AIDE MCP server entry into.mcp.json
- Merges a placeholder brain MCP entry into.mcp.json(vault path filled in by/aide)
- Writes every pipeline slash command to.claude/commands/aide/
- Installs 9 canonical pipeline agents to.claude/agents/aide/
- Installs skills (study-playbook,brain) to.claude/skills/
- Installs the methodology docs hub to.aide/docs/
- Writes theaide-treelauncher to.aide/bin/aide-tree.mjs
- Adds an AIDE badge toREADME.md(appends if not present)

All operations are additive — files that already exist are never overwritten. Safe to re-run at any time.

Pass--vault-path <path>to record your brain vault location at install time, skipping the vault-path prompt when/aidefirst runs.

After running, open Claude Code and run/aide— the orchestrator will prompt for any setup the cli could not finish (IDE choice, vault path if not supplied).

Run this after editing.aide/config/brain.aide— for example, when you update the vault path argument inmcpServerConfig.argsor rename the brain in thenamefield:

syncreads.aide/config/brain.aide, copiesmcpServerConfigverbatim into.mcp.jsonunder the fixedbrainkey, and writes thenamefield as the server label. Every other key inmcpServers(including youraideentry and any personal MCP integrations) is left byte-identical. If a legacyobsidiankey is present it is removed in the same write. The command is idempotent — running it twice produces the same.mcp.jsonbytes, and the second invocation printsalready in syncwithout touching the file. Exit code is0on success (including the no-change case),1on a missing or malformedbrain.aideor invalid.mcp.json, and2on--help.

Example output after updating the vault path inmcpServerConfig.args:

Read .aide/brain.aide Wrote brain MCP entry into .mcp.json command: npx args: [-y, obsidian-mcp, D:/notes/new-vault] Done.

If you use a client other than Claude Code, or prefer to configure manually, add the server entry to your client's MCP config file.

claude mcp add aide npx -- -y @aidemd-mcp/server@latest

Or add to your project's.mcp.json:

{ "mcpServers": { "aide": { "command": "npx", "args": ["-y", "@aidemd-mcp/server@latest"] } } }

[!NOTE] The Quick Start command above handles this automatically for Claude Code users.

- macOS:~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:%APPDATA%\Claude\claude_desktop_config.json

{ "mcpServers": { "aide": { "command": "npx", "args": ["-y", "@aidemd-mcp/server@latest"] } } }

[!NOTE] Claude Desktop does not inherit the terminal PATH. If you use nvm or Homebrew to manage Node,npxmay not be found. Runwhich npxin your terminal to get the absolute path and replace"npx"with it in the config above.

Claude Desktop requires a full quit-and-reopen after any config change.

{ "mcpServers": { "aide": { "command": "npx", "args": ["-y", "@aidemd-mcp/server@latest"] } } }

{ "servers": { "aide": { "command": "npx", "args": ["-y", "@aidemd-mcp/server@latest"] } } }

[!NOTE] VS Code / Copilot uses"servers"as the root key, not"mcpServers". Using the wrong root key causes the server to silently fail to load.

{ "mcpServers": { "aide": { "command": "npx", "args": ["-y", "@aidemd-mcp/server@latest"] } } }

Scan the project for.aidespec files and return a progressive disclosure tree map showing each spec's type, location, and summary.

- path(string, optional): Subdirectory to drill into. When provided, the response opens with the ancestor chain — the cascading intent lineage from root to target, each ancestor showing its description and alignment status — followed by the detailed subtree with summaries and warnings. When omitted, returns a shallow project-wide map (locations and types only).

Read an.aidespec file with full context, returning the file content, its classified type (intent/research/plan/todo), related specs in the same directory, and links found in the content.

- path(string, required): Path to the.aidefile to read.

Create new.aidespec files with automatic naming convention enforcement. Handles the rename rules: intent specs are.aideby default but becomeintent.aidewhenresearch.aideexists in the same folder; creating aresearch.aideauto-renames any existing.aidetointent.aide.

- directory(string, required): Directory where the.aidefile(s) will be created.
- type(string, required): Type of.aidefile to create. One of:intent,research,both,todo,plan.

Return the JSDoc block, signature, and kind for a named function, method, class, interface, or type alias in the workspace — Tier 2 progressive disclosure for code. Agents can understand a symbol's contract without opening the file.

- name(string, required): Symbol name to look up.
- file(string, optional): Restrict search to a single file (relative to project root).

Run a health check on.aidespec files in the project. Detects orphaned specs, missing specs, naming conflicts (.aideandintent.aidein the same folder), broken links, orphaned research files, and missing frontmatter descriptions.

- path(string, optional): Subdirectory to validate. Defaults to the entire project when omitted.

Boot-time precondition reporter. Returns two independent fields the orchestrator branches on separately:outdated(an array of stale AIDE artifact keys, comparing the project'sversions.jsonagainst the shipped manifest), andbrain(a{ status, name?, hints }object reporting whether the project'sbrain.aideconfig is wired into.mcp.json).brain.statusis the four-state unionok | no-brain-aide | no-mcp-entry | mcp-drift, derived by comparing.aide/config/brain.aideagainst.mcp.json— no disk path validation.nameis the user-declared label frombrain.aide(only present on non-no-brain-aidestates).hintsis an array of candidate vault locations the orchestrator can surface during recovery.

On-demand brain entry-point tool. Call this when you need to reach the brain mid-task — do NOT call it on every/aideboot. Boot-time brain precondition state is already reported byaide_info.brain.status; firingaide_brainat boot duplicates that work unnecessarily.

Returns{ status, instructions }— exactly two fields. Nobackend, noconnector, noname.statusmirrorsaide_info.brain.status(ok | no-brain-aide | no-mcp-entry | mcp-drift).instructionsis always non-empty: onokit is the verbatim## Prosebody from the user's.aide/config/brain.aide(no server substitution); on the failure states it carries fixed remediation prose naming the right CLI recovery command (npx @aidemd-mcp/server@latest initforno-brain-aide,npx @aidemd-mcp/server@latest syncforno-mcp-entryandmcp-drift).

Bootstrap the AIDE development environment into a project using a guided one-at-a-time wizard. On the first call (nocategory), returns a summary of every step with status and detected framework. On subsequent calls (withcategory), writes all pending files for that category to disk and returns a manifest.

- framework(string, optional): Force a specific framework instead of auto-detecting. One of:claude,cursor,windsurf,copilot.
- path(string, optional): Custom project root path. Defaults to the server working directory.
- category(string, optional): Write allwould-createfiles for this category and return a manifest. One of:framework,methodology,commands,agents,skills,mcp,brain,ide,readme. Omit on the first call to get a metadata-only summary.
- brainPath(string, optional): Resolved brain vault path. Required whencategory=brain.

Compare the AIDE methodology artifacts in this project against canonical versions and return a structured diff grouped by category. On the first call (nocategory), returns a lightweight summary of every category with drift status. On subsequent calls (withcategory), writes all diffed or missing files for that category to disk and returns a manifest.

- framework(string, optional): Force a specific framework instead of auto-detecting. One of:claude,cursor,windsurf,copilot.
- path(string, optional): Custom project root path. Defaults to the server working directory.
- category(string, optional): Write all drifted or missing files for this category and return a manifest. One of:pointer-stub,methodology-docs,version-metadata,commands,agents,skills,mcp,ide,readme. Omit on the first call to get a metadata-only summary.

After adding the server to your MCP client, ask your agent to runaide_initto bootstrap the AIDE methodology into your project. This installs the methodology docs, scaffolds pipeline commands, and wires everything up.

Then try: "Scaffold an intent spec for my authentication module" — the agent will useaide_discoverto map your project andaide_scaffoldto create the spec in the right place with the right naming conventions.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

An MCP server that enforces rules from markdown files for AI agents. This is a zero-tool version that requires an external rules file.

Automatic documentation updates from agents, and codebase conventions to reduce token usage.

Token-efficient MCP server for Odoo 17/18/19 development. It gives AI assistants structured access to your Odoo codebase for discovery, search, model/view analysis, XML checks, and scaffolding patches.

Paid remote MCP for ZeroLang, structured receipts, usage logs, and audit-ready JSON evidence.

Local stdio MCP server that lets AI coding agents read and maintain structured architecture, rules, and decisions directly from your repository.

The MCP server for Bitrix24 provides AI assistants with structured access to the Bitrix24 API. It delivers up-to-date method descriptions, parameters, and valid values, allowing assistants to work with precise data instead of guesswork. This reduces code errors and accelerates Bitrix24 integration development.

Official Context7 MCP server that brings up-to-date, version-specific library documentation and code examples into AI coding prompts.

Remote, no-auth MCP server providing AI-powered codebase context and answers

Official Svelte MCP server, provides docs and suggestions on the generated code.

Execute any LLM-generated code in the YepCode secure and scalable sandbox environment and create your own MCP tools using JavaScript or Python, with full support for NPM and PyPI packages