mcp

A local Model Context Protocol server, a small program that lets an AI assistant call defined tools. MindLink uses it to let agents read and update project memory with checked data formats.

In plain words
What is it for?
Use it to provide an AI agent with selected memory sections, write updates to MindLink memory, and verify that a memory write succeeded.
Why use it?
It connects Claude Code to the project’s memory files and helps prevent invalid or misplaced updates. Claude Code starts it automatically when MindLink is configured for Claude Code.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/404-not-found/mindlink/mcp
Clone the repo
git clone --depth 1 https://github.com/404-not-found/mindlink
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 877 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00877
Opus 5 $0.00000 $0.00439
Sonnet 5 $0.00000 $0.00175
Haiku 4.5 $0.00000 $0.00088

Measured 3d ago against content hash 62f874b58213, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/mcp.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start the MindLink MCP server for AI tool integration.


Synopsis

mindlink mcp

Description

mindlink mcp starts a local Model Context Protocol server over stdio. It exposes 4 tools that AI agents (like Claude Code) can call to read and write memory with schema validation and structured responses.

This command is launched automatically by Claude Code — you do not need to run it yourself. When you run mindlink init and select Claude Code, MindLink adds the MCP server entry to .claude/settings.json so Claude Code starts it on every session.

Why MCP?

  • Schema-validated writes — the AI can't accidentally overwrite the wrong section
  • Structured reads — returns only the sections needed for the current task (token-efficient)
  • Verify loop — the AI can call mindlink_verify() after writing to confirm the write succeeded

Tools

mindlink_read_memory(section?)

Read a section of this project's MEMORY.md.

  • No argument: returns Core + User Profile only (the recommended default at session start)
  • With section: returns just that section
Section value Content
Core Project identity, stack, top decisions
Architecture System design decisions
Decisions Key choices made and why
Conventions Team patterns and coding standards
User Profile Personal facts about the user
Important Context Business context, deadlines, preferences

mindlink_write_memory(section, content)

Append a fact or decision to a section of MEMORY.md.

Never overwrites existing content — always appends. Always include a <!-- added: YYYY-MM-DD --> timestamp in the content.


mindlink_session_update(summary)

Overwrite SESSION.md with a summary of the current session.

Call this as the last action of every response. SESSION.md is temporary; it gets cleared between sessions. MEMORY.md is permanent.

Read the full file on GitHub · 127 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 127 lines · 0 tokens per session scan A 62f874b58213

Subscribe to this mod's changes

mcp is a command published in the GitHub repository 404-not-found/mindlink (11 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 877 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.