What is capacitiesMCP CLAUDE.md?

Repository instructions for an MCP server that connects to Capacities, a note-taking and knowledge-management service.

Use them when compiling, testing, running, or inspecting this TypeScript server and its Capacities API integration.

They document the build, development, testing, debugging, and API-token setup needed to work on the server.

How inconceivablelabs/capacitiesMCP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to inconceivablelabs/capacitiesMCP. 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/inconceivablelabs/capacitiesMCP/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/inconceivablelabs/capacitiesMCP

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/inconceivablelabs/capacitiesmcp/claude-md/github.svg)](https://agentmods.dev/instructions/inconceivablelabs/capacitiesmcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/inconceivablelabs/capacitiesmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/inconceivablelabs/capacitiesmcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/inconceivablelabs/capacitiesmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/inconceivablelabs/capacitiesmcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 7,707 This file is loaded in full into every session.

When invoked 7,707 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.07707	$0.07707
Opus 5.5	$0.03083	$0.03083
Sonnet 5.5	$0.01541	$0.01541
Haiku 4.5	$0.00771	$0.00771

Measured 2d ago against content hash 69236691ae2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

capacitiesMCP CLAUDE.md 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 2d 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.

CLAUDE.md · 351 lines

How it starts

The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Development Commands

Build and Development

Build: npm run build - Compiles src/ to server/dist/ and makes index.js executable
Development: npm run dev - Watch mode compilation with TypeScript
Start: npm run start - Run the compiled MCP server
Inspector: npm run inspector - Launch MCP Inspector for debugging tools
Test: npm test - Compiles tsconfig.test.json then runs the Node.js built-in test runner (node --test) over test-dist/test/**/*.test.js

The gates are npm run build (tsc) + npm test. Tests use mocked fetch (no live token, no network) — see test/.

Environment Setup

Required environment variables:

CAPACITIES_API_TOKEN - v2 API token (cap-api-…) from the Capacities desktop app (required)
CAPACITIES_API_BASE_URL - API base URL (optional, defaults to https://api.capacities.io)
LOG_LEVEL - Logging level (optional, defaults to "info"; set debug to emit response-body DEBUG logs)

Dependencies

@modelcontextprotocol/sdk: MCP protocol implementation
zod: Schema validation for tool parameters
dotenv: Environment variable loading from .env files
typescript: TypeScript compilation

Architecture Overview

This is an MCP (Model Context Protocol) server integrating Claude with the Capacities knowledge management platform. It runs on the Capacities v2 REST API (developers.capacities.io), migrated from the v1 Beta API (which sunsets 2026-09-01). It exposes a small generic core — search, structure introspection, and object CRUD — and lets the LLM compose those into workflows.

v2 API essentials:

Bearer cap-api-… token; every request sends the header X-Capacities-Api-Version: 1.0.0 (the spec version; bumped from 0.1.0 in cap-6au after reads + a 400 diffed identical).
A token is scoped to a single space. GET /space is singular; search takes no spaceId. Multi-space = multiple tokens. There is no space_id parameter on any tool.

Read the full file on GitHub · 351 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.

2d ago Changed · -12 tokens per session 69236691ae2a
3d ago Changed · +31 lines · +615 tokens per session e86df047ef8c
14d ago Changed · +55 lines · +1,433 tokens per session 79cf6a20ebe3
15d ago Changed · +15 lines · +758 tokens per session 6374153fd7fb
2mo ago First seen · 250 lines · 4,913 tokens per session scan A 48b941da9e9d

Subscribe to this mod's changes

capacitiesMCP CLAUDE.md is an instructions file published in the GitHub repository inconceivablelabs/capacitiesMCP (7 stars, last pushed 3d ago), licensed MIT. It adds 7,707 tokens to every session, about $0.0308 per session on Opus 5.5. 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 2026-08-31.

Documents Productivity

capacitiesMCP CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
capacitiesMCP CLAUDE.mdinconceivablelabs/capacitiesMCP	Instructions file	7	3d ago	MIT	A	7,707	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

capacitiesMCP: Instructions file for Claude Code