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.
npx agentmods add instructions/ckalima/pipedrive-mcp-server/claude-mdgit clone --depth 1 https://github.com/ckalima/pipedrive-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/ckalima/pipedrive-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/ckalima/pipedrive-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/ckalima/pipedrive-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01497 | $0.01497 |
| Opus 5 | $0.00749 | $0.00749 |
| Sonnet 5 | $0.00299 | $0.00299 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
pipedrive-mcp-server 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipedrive MCP Server
MCP server providing Pipedrive CRM tools over STDIO transport. TypeScript, Node.js.
Commands
npm run build # TypeScript compile (tsc)
npm test # Run all tests (vitest)
npm run dev # Dev mode with tsx
npm start # Run compiled server
npm run test:coverage # Coverage report
Architecture
src/
index.ts # MCP server entry point (STDIO transport)
client.ts # Singleton PipedriveClient (lazy init, API calls); drives the resilience retry/breaker loop below fetch
resilience.ts # Retry classifier, full-jitter backoff, Retry-After parsing, per-process circuit breaker (sits below the client chokepoint)
version-routing.ts # v1-only capability seam: routes the four v1 capabilities + lazy sunset/retirement detection (sits above the client)
capability-modes.ts # Resolves PIPEDRIVE_MODE → read-only/safe-write/full; pure tool-reachability classification + tools/list filtering (no new per-tool metadata)
config.ts # Environment validation (PIPEDRIVE_API_KEY, PIPEDRIVE_MODE, PIPEDRIVE_ENABLE_DESTRUCTIVE); shared API-key format predicate + base URLs
identity.ts # Connected-account identity: one bounded GET /users/me (v1) per process at boot, bypassing the version-routing seam; startup banner lines + the one-shot `connection` notice appended to the first tool response
cli/ # `npx … init` guided installer (subcommand routed from index.ts; not the STDIO server path)
init.ts # Interactive flow orchestration + flag parsing; injectable IO seams (readline/opener/validator/writer)
config-targets.ts # Host descriptor table + renderer (per-OS path, top-level key, committed→indirection secret mechanism)
verify-key.ts # Pasted-key validation via createValidationClient → GET /users/me (v1), bypassing the version-routing seam
write-config.ts # Non-destructive config writer (read-merge-backup-atomic write, 0600, symlink/TOCTOU-safe) + `claude mcp add` builder
open-url.ts # Best-effort detached browser opener (env scrubbed of PIPEDRIVE_API_KEY)
tools/ # MCP tool handlers (one file per entity)
index.ts # Tool registration, allTools array, getToolHandler/getToolSchema/getTool
schemas/ # Zod input validation (one file per entity, common.ts for shared)
utils/
errors.ts # Error types, getErrorResponse, destructiveOperationGuard
formatting.ts # createListSummary
pagination.ts # v1 (offset) and v2 (cursor) pagination helpers
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.
- 5d ago First seen · 87 lines · 1,497 tokens per session scan A 2b42ba11b104
pipedrive-mcp-server CLAUDE.md is an instructions file published in the GitHub repository ckalima/pipedrive-mcp-server (8 stars, last pushed 6d ago), licensed MIT. It adds 1,497 tokens to every session, about $0.0075 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.
Other instructions, from other repositories
smartmoving-mcp AGENTS.md
Instructions for MattyMailers/smartmoving-mcp, covering ai agent contribution guide, project purpose, before editing, safe contribution lanes and hard safety rules.
neon-mcp-server CLAUDE.md
Claude Code instructions for voyagi/neon-mcp-server, covering neon mcp server — upwork portfolio project, purpose, what to build, demo scenario: "techstart crm" and value proposition.
localtry-mcp AGENTS.md
AGENTS.md instructions for philly88r/localtry-mcp, a project described as: Tenant-isolated MCP server for operating and customizing LocalTry CRM from ChatGPT and other AI clients.
livespace-crm-mcp AGENTS.md
AGENTS.md instructions for proAutomator/livespace-crm-mcp, covering livespace-crm-mcp - agent instructions, hard rules, livespace api - facts that will bite you, design canon and milestone workflow.
pipedrive-mcp CLAUDE.md
Instructions for comma-compliance/pipedrive-mcp, covering pipedrive mcp server, build instructions, architecture rules, testing and key files.
godcrm AGENTS.md
AGENTS.md instructions for Holetron-lab/godcrm, covering gitnexus — code intelligence, always do, never do, resources and cli.