What is livespace-crm-mcp AGENTS.md?

Repository instructions for building an unofficial Livespace CRM server, including security rules, technical choices, and the development workflow. Livespace CRM is a customer-management system.

Use it when changing authentication, the CRM connection, network transport, error handling, tests, or the design and milestone workflow.

It keeps coding work aligned with project rules and reduces risks such as exposing credentials, customer data, tokens, or unsafe error details.

How proAutomator/livespace-crm-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to proAutomator/livespace-crm-mcp. 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/proAutomator/livespace-crm-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/proAutomator/livespace-crm-mcp

Made for: Codex, OpenCode.

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/proautomator/livespace-crm-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/proautomator/livespace-crm-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/proautomator/livespace-crm-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/proautomator/livespace-crm-mcp/agents-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/proautomator/livespace-crm-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/proautomator/livespace-crm-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,100 This file is loaded in full into every session.

When invoked 1,100 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	$0.01100	$0.01100
Opus 5.5	$0.00440	$0.00440
Sonnet 5.5	$0.00220	$0.00220
Haiku 4.5	$0.00110	$0.00110

Measured 2mo ago against content hash d71657e7a57a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

livespace-crm-mcp AGENTS.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.

AGENTS.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

livespace-crm-mcp - Agent Instructions

Unofficial MCP server for Livespace CRM. ~10 intent-shaped tools instead of a 1:1 mirror of the ~80-method RPC API. Target protocol: MCP 2026-07-28 (stateless Streamable HTTP). Stack: TypeScript (strict) + Hono, Bun/Node with a planned Cloudflare Workers dual runtime, @modelcontextprotocol/server v2 pinned to an exact version.

Hard rules

Read docs/security.md before touching auth, the Livespace client, transport, or error handling. Its MUSTs are binding; code violating them does not ship.
No secrets, no real CRM data - anywhere. Not in code, tests, fixtures, docs, commit messages, or .ai/ files. Fixtures are synthetic and every fake credential value MUST contain the word "synthetic" (e.g. synthetic-key-123) - .gitleaks.toml allowlists that marker and nothing else, so CI stays green without weakening the scanner. This repo's full history is expected to become public.
Never log tokens or full CRM payloads. Errors surfaced to the model must never contain upstream response bodies or stack traces.
TDD. Write the failing test first. Every tool ships with contract tests; security regressions from docs/security.md §10 stay green.
English for code, comments, commits, and docs.
Do not change the default bind (127.0.0.1) or weaken fail-closed startup checks without an explicit maintainer decision.
Do not commit or push unless Kuba asks.

Livespace API - facts that will bite you

Success is status: true && result: 200 in the response envelope; HTTP is 200 even on errors. Always check the envelope.
The official Postman docs contain errors (e.g. "delete deal" shown as Contact/deleteDeal; PDF v1.13 says Deal/deleteDeal). Trust the API PDF over the Postman portal and confirm every method with a live smoke test on a sandbox account before release.
Deal/getAll requires at least one condition. List endpoints default to returning ALL records - send an explicit limit where the endpoint supports it. Todo/getTodoObjects uses fixed 50-row pages; dictionary endpoints that ignore limit need bounded local caps.
There is no "set stage" call: stage changes = marking process steps via editDeal stages{step_id: 0|1} mapped from Deal/process_getList.
Every logical call costs 2 HTTP requests (auth token + call): batch aggressively, cache dictionaries in memory with TTL.
Select-type custom fields (datasets) take answer IDs, not display text.

Read the full file on GitHub · 84 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 First seen · 84 lines · 1,100 tokens per session scan A d71657e7a57a

Subscribe to this mod's changes

livespace-crm-mcp AGENTS.md is an instructions file published in the GitHub repository proAutomator/livespace-crm-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 1,100 tokens to every session, about $0.0044 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.

automation bun crm mcp model-context-protocol sales

livespace-crm-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
livespace-crm-mcp AGENTS.mdproAutomator/livespace-crm-mcp	Instructions file	0	4d ago	MIT	A	1,100	Codex, OpenCode
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

livespace-crm-mcp: Instructions file for Codex