What is mcp-planner CLAUDE.md?

Project instructions for building an MCP server that connects Microsoft Planner with Microsoft Graph, Microsoft's API for accessing its services.

Building, testing, running, and packaging the Microsoft Planner integration, including its Graph API client, HTTP access, and MCP tools.

They document the expected commands, architecture, authentication, resource types, and update rules so contributors can extend the server consistently.

How mspstack/mcp-planner configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mspstack/mcp-planner. 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/mspstack/mcp-planner/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mspstack/mcp-planner

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/mspstack/mcp-planner/claude-md/github.svg)](https://agentmods.dev/instructions/mspstack/mcp-planner/claude-md)

Your own site

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

Per session 1,052 This file is loaded in full into every session.

When invoked 1,052 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	$0.01052	$0.01052
Opus 5.5	$0.00421	$0.00421
Sonnet 5.5	$0.00210	$0.00210
Haiku 4.5	$0.00105	$0.00105

Measured 2mo ago against content hash 57d9358eb6d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-planner 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 2mo 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 · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

MCP server for Microsoft Planner via Microsoft Graph. Sibling project to mcp-connectwise-psa (copied from it) and mcp-itglue — same architecture.

Commands

npm run build — tsc to dist/
npm test — vitest
npm run dev / npm run dev:http — tsx, stdio or HTTP transport
npm run bundle — build the Claude Desktop .mcpb

Architecture

src/index.ts — CLI entry; --transport stdio|http, --port; USAGE text
src/config.ts — loadConfig(argv, env) → ServerConfig; ConfigError; MS_* env vars
src/server.ts — createServer(session) builds a per-session McpServer; INSTRUCTIONS string
src/graph/client.ts — GraphClient: client-credentials token (cached, 60s skew), get/getList/post/patch/delete; PATCH/DELETE take an explicit etag (If-Match); PATCH sends Prefer: return=representation; GraphApiError + describeError
src/graph/types.ts — Graph resource shapes; priorityLabel/PRIORITY_VALUES/progressLabel
src/http/app.ts — Express app; BYOK via x-ms-tenant-id/x-ms-client-id/x-ms-client-secret headers with fallback to server env creds; session principal pinned by SHA-256 hash
src/tools/registrar.ts — ToolRegistrar; no MCP-level role gating (Graph is the access control)
src/tools/shared.ts — zod fragments (responseFormatField, topField), text/failure/json/clip
src/tools/{groups,plans,tasks}.ts — planner_* tools; plans.ts includes planner_list_my_plans (/me/planner/plans delegated, /users/{id}/planner/plans with user_id)
src/tools/session.ts — planner_whoami: app-only vs delegated (+ acting user via /me); mode detection is GraphClient.isDelegated
src/tools/advanced.ts — opt-in escape hatch (PLANNER_ADVANCED_TOOLSET=true / --advanced, off by default): graph_get (read-only GET via the verb-locked GraphClient.get, allowlisted to /planner, /groups, /users — plus /me on delegated sessions; /beta rejected; a pasted @odata.nextLink works as path — its inline query is parsed and merged, structured args win) and graph_find_endpoint (lexical search over the hand-maintained src/reference/graph-endpoints.ts). Search functions kept in sync with mcp-connectwise-psa's advanced.ts

Read the full file on GitHub · 63 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.

2mo ago Changed · +8 lines · +195 tokens per session 57d9358eb6d6
2mo ago First seen · 55 lines · 857 tokens per session scan A 64469fe5aaee

Subscribe to this mod's changes

mcp-planner CLAUDE.md is an instructions file published in the GitHub repository mspstack/mcp-planner (4 stars, last pushed 2mo ago), licensed MIT. It adds 1,052 tokens to every session, about $0.0042 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.

Backend and APIs Project management

mcp-planner CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-planner CLAUDE.mdmspstack/mcp-planner	Instructions file	4	2mo ago	MIT	A	1,052	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

mcp-planner: Instructions file for Claude Code