pipedrive-mcp CLAUDE.md

pipedrive-mcp CLAUDE.md is an instructions file for Claude Code from comma-compliance/pipedrive-mcp. It costs 284 tokens per session, scanned A, original, MIT.

Repository instructions for a TypeScript server that connects to Pipedrive through its API and exposes tools for working with Pipedrive data.

In plain words
What is it for?
Use them when adding Pipedrive entities, schemas, API calls, custom-field handling, tests, or destructive operations that need confirmation and dry-run support.
Why use it?
They give contributors the project’s build, test, architecture, API-routing, typing, and safety rules in one place.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

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 instructions/comma-compliance/pipedrive-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/comma-compliance/pipedrive-mcp

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 pipedrive-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/comma-compliance/pipedrive-mcp/claude-md.svg)](https://agentmods.dev/instructions/comma-compliance/pipedrive-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/comma-compliance/pipedrive-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/comma-compliance/pipedrive-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 284 This file is loaded in full into every session.
When invoked 284 The same file — it is already loaded in full.
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 5.1 $0.00284 $0.00284
Opus 5 $0.00142 $0.00142
Sonnet 5 $0.00057 $0.00057
Haiku 4.5 $0.00028 $0.00028

Measured 5d ago against content hash 9bef64cd584a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

pipedrive-mcp 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 5d 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 · 31 lines

What it actually says

Pipedrive MCP Server

Build instructions

  • npm install && npm run build
  • npm run dev (watch mode)
  • npm test (vitest)

Architecture rules

  • One tool file per entity in src/tools/
  • One schema file per entity in src/schemas/
  • No business logic in tool handlers - delegate to services/
  • No raw HTTP in tool files - use api-v1.ts or api-v2.ts via http-client.ts
  • No @ts-ignore - fix types properly
  • No hardcoded Pipedrive field keys or option IDs
  • All destructive tools require confirm param and support dry_run
  • Use native fetch (not axios)
  • Use Zod .strict() on all tool input schemas
  • v2 activities use participants array, not person_id (which is read-only)
  • v2 custom field writes must nest fields in a custom_fields object
  • All field metadata endpoints are v1 (v2 field routes are not available on all instances)

Testing

  • vitest for all tests
  • nock for HTTP mocking in integration tests
  • Never hit production Pipedrive in tests
  • Sanitized fixtures in test/fixtures/v1/ and test/fixtures/v2/

Key files

  • src/pipedrive/endpoint-policy.ts is the source of truth for API routing
  • src/services/custom-fields.ts handles all field name resolution
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. 5d ago First seen · 31 lines · 284 tokens per session scan A 9bef64cd584a

Subscribe to this mod's changes

pipedrive-mcp CLAUDE.md is an instructions file published in the GitHub repository comma-compliance/pipedrive-mcp (8 stars, last pushed 4mo ago), licensed MIT. It adds 284 tokens to every session, about $0.0014 per session on Opus 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.