serverBLOCK
MCP server that teaches any AI agent the AIDE spec methodology — progressive disclosure specs alongside code
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/aidemd-mcp/server) [](https://github.com/aidemd-mcp/server/actions/workflows/ci.yml) [](https://www.npmjs.com/package/@aidemd-mcp/server) [](https://opensource.org/licenses/MIT) [](https://glama.ai/mcp/servers/aidemd-mcp/server) [](https://www.npmjs.com/package/@aidemd-mcp/server) [](https://www.typescriptlang.org/) [](https://discord.gg/N4NqMXuvTR)
MCP server that brings intent-driven development to any AI-powered IDE. Manage .aide spec files that live next to your code — the domain context that architects plan from, implementors build from, and QA validates against.
Learn more at aidemd.dev.
Features
- Project-wide spec discovery with a progressive disclosure tree that surfaces intent, research, and QA specs at every level of your codebase
- One-command project bootstrap via
aide_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 - Guarded pipeline cleanup via
aide_cleanup— removes a closed module's plan, todo and brief only when every checkbox is checked, and refuses with the exact open items otherwise - **Health-check valid
f68c7b958c30OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add server -- npx -y @aidemd-mcp/[email protected]
Exposed tools (5)
4 read · 0 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
aide_cleanup | destructive | Remove a module |
aide_discover | read | Scan for .aide spec files in this project. Returns a tree map of where specs live, following progressive disclosure.\n\nWithout a path: returns a lightweight project-wide map — file locations and types only, no content. Use this once to understand the project |
aide_info | read | Boot-time reporter called by the orchestrator at startup. Returns independent top-level fields that the orchestrator must branch on separately:\n\n** |
aide_init | read | Bootstrap the AIDE development environment into a project. Returns structured JSON for agent consumption — not prose.\n\nThe tool uses a two-call pattern for progressive disclosure:\n\n**First call (no |
aide_read | read | Read an .aide spec file with full context. Returns the file content, its classified type (intent/research/plan/todo), related specs in the same directory, and links found in the content (relative paths, inline references, URLs). Use this after aide_discover to drill into a specific spec. |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- declared (1 observation(s))
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (19)
After Step 6 completes, **STOP**. Do NOT call `aide_info` again in this session. The brain MCP server was launched before the new entry existed and cannot be hot-reloaded mid-session — an in-session r
aide_cleanup
.aide
.mcp.json.example
.prettierignore
.aide
.aide
import brainContract from "../../brainContract/index.js";
import obsidianBrainAideTemplate from "../../obsidianBrainAideTemplate/index.js";
import detectBrainMigration from "../../detectBrainMigration/index.js";
import detectBrainMigration from "../../detectBrainMigration/index.js";
import isTemplateIntegration from "../../isTemplateIntegration/index.js";
@modelcontextprotocol/sdk, ink, react, typescript, yaml, zod, @types/marked, @types/node
5. **Restart Claude Code** so the new MCP server loads. MCP server registration is read at client startup; an edit + sync without a restart leaves the running session pointing at the previous brain.
6. **Drift detected** by the boot reporter. At session start, the reporter compares the `brain` entry in `.mcp.json` against the values declared in `brain.aide`. If they disagree, the reporter surface
5. Every subagent call needs three things: a type (`read-only` for exploration, or `general-purpose` for full access), a short description for the UI (5–10 words), and the full prompt the subagent rec
If the user says ignore, proceed.
- **NEEDS_DISCUSSION:** hard stop. Wait for the user's direction. If the user says proceed, ask "Ready to stash?" If yes, run the [[kanban/guide/stash|Stash]] operation.
If the user says yes, run Steps 4a through 4d below. You are an orchestrator: delegate every step to subagents.
Gates applied: critical_finding, no_behavioural_pass, undeclared_transfer.
f68c7b958c30full audit observations/trust-audit/mcp-server/aidemd-mcp__server.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | f68c7b958c30 | BLOCK | D | 69 | first audit |
Questions
What is the server MCP server?
MCP server that teaches any AI agent the AIDE spec methodology — progressive disclosure specs alongside code
What tools does server expose?
5 in total: 4 read-only, 0 that write, and 1 that can delete or overwrite (aide_cleanup). Every one is listed on this page with its risk.
Is server safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does server need?
No credential environment variables were found in its source, so it appears to need none.
How does server run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @aidemd-mcp/server at 0.11.1.
How current is this page?
The grade is for one exact copy of the source (f68c7b958c30), read on 2026-10-11. The repository is watched and re-audited when it changes.