MCP-Context-Provider: Instructions file for Claude Code

CLAUDE.md

MCP-Context-Provider CLAUDE.md is an instructions file for Claude Code from doobidoo/MCP-Context-Provider. It costs 2,480 tokens per session, scanned B, original, Apache-2.0.

Development instructions for an MCP server called mcp-context-provider, which supplies coding agents with saved context and learned session notes. They describe its TypeScript architecture, commands, and tests.

In plain words
What is it for?
Use them when developing, building, testing, or reviewing the mcp-context-provider project, including its MCP server, command-line tool, validation, and memory connection.
Why use it?
They give contributors a shared explanation of how the project is organised and how its context and memory features work, reducing guesswork when changing the code.

Instructions file for Claude Code

Written for Claude Code: UserPromptSubmit hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is doobidoo/MCP-Context-Provider's own configuration. It tells Claude Code how to work on MCP-Context-Provider itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MCP-Context-Provider configures →

Reuse

Borrowing it

Nothing to install: this file belongs to doobidoo/MCP-Context-Provider. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/doobidoo/MCP-Context-Provider/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/doobidoo/MCP-Context-Provider

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for MCP-Context-Provider CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/doobidoo/mcp-context-provider/claude-md.svg)](https://agentmods.dev/instructions/doobidoo/mcp-context-provider/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/doobidoo/mcp-context-provider/claude-md"><img src="https://agentmods.dev/badge/instructions/doobidoo/mcp-context-provider/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,480 This file is loaded in full into every session.
When invoked 2,480 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02480 $0.02480
Opus 5 $0.01240 $0.01240
Sonnet 5 $0.00496 $0.00496
Haiku 4.5 $0.00248 $0.00248

Measured 4d ago against content hash a59025f7c3d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

MCP-Context-Provider CLAUDE.md scanned grade B with 1 finding 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Register in `~/.claude/settings.json` under both `UserPromptSubmit` and `PostToolUse`:
CLAUDE.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — mcp-context-provider (v2.0 beta)

Clean rewrite from Python v1.8.x to TypeScript.

Architecture

Two core concepts:

  • Contexts (static): 200–1000 tokens, manually authored, always injected at full confidence
  • Instincts (learned): 20–80 tokens, distilled from sessions, confidence-scored (0.0–1.0), human-approved

Four subsystems:

  • Engine — loads, matches, and merges contexts + instincts into injection payloads
  • MCP Server (src/server/index.ts) — stdio + HTTP transport, 6 MCP tools
  • CLI (mcp-cp) — approval registry for instinct lifecycle management
  • Memory Bridge — syncs instincts to mcp-memory-service via HTTP API

Project Structure

src/
  server/             MCP Server (stdio + HTTP transport)
    index.ts          Entry point, tool handlers, transport selection
  types/              TypeScript type definitions
    instinct.ts       Instinct, OutcomeEntry, InstinctCandidate, InstinctQuery
    context.ts        Context, StoreTrigger, RetrieveTrigger, ContextMetadata
    index.ts          Re-exports
  schema/             Zod validation schemas
    instinct.schema.ts
    context.schema.ts
  config/             Path resolution
    paths.ts          Store/contexts path resolution (shared by server + CLI)
  engine/             Core engines
    engine.ts         Unified Engine (contexts + instincts + memory bridge)
    context-loader.ts JSON context discovery + validation
    context-matcher.ts Tool-pattern matching with glob support
    instinct-loader.ts YAML load/save with Zod validation
    instinct-matcher.ts Regex trigger-pattern matching
  bridge/             Memory Bridge (mcp-memory-service integration)
    types.ts          IMemoryBridge interface, config, response types
    http-bridge.ts    HTTP implementation (fetch-based, zero deps)
    sync.ts           Bidirectional YAML ↔ Memory sync
  cli/                Approval Registry CLI (mcp-cp)
    index.ts          CLI entry point + argument parser
    registry.ts       approve/reject/tune/outcome/remove operations
    formatter.ts      ANSI terminal formatting

hooks/                Claude Code hooks
  instill-trigger.js  Auto-detect corrections/failures → nudge /instill
instincts/            learned.instincts.yaml — the one instinct store
contexts/             JSON context files (*_context.json)
.claude/skills/       Claude Code skills
  instill.md          /instill — distill instincts from session

Read the full file on GitHub · 254 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. 4d ago Changed · +8 lines · +121 tokens per session a59025f7c3d6
  2. 8d ago First seen · 246 lines · 2,359 tokens per session scan B f1dd6db49fb9

Subscribe to this mod's changes

MCP-Context-Provider CLAUDE.md is an instructions file published in the GitHub repository doobidoo/MCP-Context-Provider (30 stars, last pushed 5d ago), licensed Apache-2.0. It adds 2,480 tokens to every session, about $0.0124 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens