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/tylerilunga/procore-mcp-server/claude-mdgit clone --depth 1 https://github.com/TylerIlunga/procore-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/tylerilunga/procore-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/tylerilunga/procore-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/tylerilunga/procore-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 | $0.02345 | $0.02345 |
| Opus 5 | $0.01172 | $0.01172 |
| Sonnet 5 | $0.00469 | $0.00469 |
| Haiku 4.5 | $0.00234 | $0.00234 |
Grade A, and why
procore-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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Procore MCP Server
MCP server exposing the full Procore REST API for Claude Desktop and Claude Code. Single-user OAuth. TypeScript + @modelcontextprotocol/sdk.
Quick Start
npm install
npm run build # Generate catalog from OAS + compile TypeScript
npm run auth # One-time: OAuth flow to get Procore tokens
npm start # Start MCP server (stdio transport)
Architecture
7 MCP tools provide full coverage of Procore API endpoints:
| Tool | Purpose |
|---|---|
procore_discover_categories |
List API categories with endpoint counts |
procore_discover_endpoints |
List endpoints in a category/module |
procore_get_endpoint_details |
Get full parameter schema for an endpoint |
procore_api_call |
Execute any Procore API call |
procore_search_endpoints |
Full-text search across endpoints |
procore_get_config |
Show current config (company_id, auth status) |
procore_set_config |
Set runtime config (company_id, project_id) |
Build Pipeline
specs/combined_OAS.json (~54MB) -> scripts/generate-catalog.ts -> data/catalog.json + data/endpoint-details/ -> scripts/generate-tools-manifest.ts -> data/tools-manifest.json
Current spec (2026-08-04): 3,155 operations -> 2,929 generated tools + 7 meta tools.
The manifest drops older-version duplicates of the same path and the
non-callable /oauth/* endpoints; both stay reachable via procore_api_call.
Tool Description Quality
Generated tool descriptions are assembled from one sentence per scoring dimension, and no sentence may restate another:
| Module | Responsibility |
|---|---|
src/tools/resource-label.ts |
Names the actual resource from the OAS summary (never the category) |
src/tools/purpose-builder.ts |
Verb-aware purpose synthesis (a reorder is never described as a create) |
src/tools/description-builder.ts |
Deprecation notice, usage guidance, prerequisites, assembly |
src/tools/behavior-builder.ts |
Return shape, side effects, failure modes |
src/tools/param-descriptions.ts |
Per-parameter prose and source hints |
src/tools/annotation-builder.ts |
Titles and MCP annotations |
src/tools/version-sibling-note.ts |
Names cross-version sibling tools in the description |
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 · 191 lines · 2,345 tokens per session scan A 3806409e295f
procore-mcp-server CLAUDE.md is an instructions file published in the GitHub repository TylerIlunga/procore-mcp-server (9 stars, last pushed 14d ago), licensed MIT. It adds 2,345 tokens to every session, about $0.0117 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
clawstash CLAUDE.md
Claude Code instructions for fo0/clawstash, covering claude.md -- project guide, session start -- read order, workflow triggers, output languages and performance / modes.
sidewise CLAUDE.md
Claude Code instructions for nulljosh/sidewise, covering sidewise, architecture, endpoints, develop and tests.
clawstash AGENTS.md
AGENTS.md instructions for fo0/clawstash, covering agents.md — agent guide and gitnexus — read-only analysis policy (non-negotiable).
acikpoz copilot-instructions.md
Copilot instructions for gulmezeren2-byte/acikpoz, covering copilot instructions — acikpoz, build, test, lint, architecture and conventions.
mcp-server AGENTS.md
AGENTS.md instructions for NannyKeeper/mcp-server, covering nannykeeper mcp server — agent instructions, purpose, tools available, when to use and key facts.
mcp-server CLAUDE.md
Claude Code instructions for NannyKeeper/mcp-server, covering nannykeeper mcp server, tools, setup and context for ai assistants.