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/tigrisdata/mcp-oidc-provider/agents-mdgit clone --depth 1 https://github.com/tigrisdata/mcp-oidc-providerWrote 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/tigrisdata/mcp-oidc-provider/agents-md)<a href="https://agentmods.dev/instructions/tigrisdata/mcp-oidc-provider/agents-md"><img src="https://agentmods.dev/badge/instructions/tigrisdata/mcp-oidc-provider/agents-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 | $0.00634 | $0.00634 |
| Opus 5 | $0.00317 | $0.00317 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
mcp-oidc-provider 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 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions for mcp-oidc-provider
Overview
This is mcp-oidc-provider - an Express middleware that acts as an OIDC provider for MCP (Model Context Protocol) servers with support for any OIDC-compliant identity provider as its backend.
Key Concepts
- OIDC Provider: Acts as a man-in-the-middle between MCP clients and upstream identity providers
- Two Deployment Modes:
- Standalone: Separate OIDC server, MCP server proxies auth requests to it
- Integrated: Single Express app hosting both OIDC and MCP
- Storage: Uses Keyv for abstraction - supports any Keyv-compatible backend (Tigris, Redis, in-memory)
Project Structure
src/oidc/- Core OIDC server implementation (createOidcServer,OidcClient)src/mcp/- MCP-specific utilities (setupMcpExpress,createMcpAuthProvider)src/core/- Core provider implementationsrc/utils/- Utilities (JWKS generation, etc.)example/- Example implementations
Development Commands
npm run build # Build the project
npm run dev # Watch mode for development
npm run lint # Lint TypeScript code
npm run lint:fix # Auto-fix lint issues
npm run format # Format code with Prettier
npm run format:check # Check formatting
npm run type-check # Type check without emitting
npm test # Run tests
npm run test:watch # Watch mode for tests
npm run test:coverage # Run tests with coverage
Code Style
- Use ESLint and Prettier configurations in the project
- Follow TypeScript best practices
- Run
npm run lint:fixandnpm run formatbefore committing
Testing
- Tests are written with Vitest
- Coverage is tracked via Codecov
- Run
npm run test:coveragebefore submitting PRs
Commit Messages
Must follow Conventional Commits format:
feat:- New featuresfix:- Bug fixesdocs:- Documentation changesrefactor:- Code refactoringtest:- Adding or updating testschore:- Maintenance tasks
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 · 75 lines · 634 tokens per session scan A 64e856e0b5dd
mcp-oidc-provider AGENTS.md is an instructions file published in the GitHub repository tigrisdata/mcp-oidc-provider (13 stars, last pushed today), licensed MIT. It adds 634 tokens to every session, about $0.0032 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 2026-08-30.
Other instructions, from other repositories
casdoor CLAUDE.md
Claude Code instructions for casdoor/casdoor, a project described as: An open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD.
authprobe AGENTS.md
Instructions for authprobe/authprobe, covering agents.md, code map, layer boundaries, invariants and golden principles.
pi-anthropic-auth AGENTS.md
AGENTS.md instructions for gotgenes/pi-anthropic-auth, covering agents guide: pi-anthropic-auth, project, primary goal, current status and principles.
pixiv-cli AGENTS.md
AGENTS.md instructions for FlanChanXwO/pixiv-cli, covering agents.md, 核心命令, 边界规则, 注意事项 and 文档路由.
pixiv-cli copilot-instructions.md
Copilot instructions for FlanChanXwO/pixiv-cli, covering pixiv cli copilot instructions, project shape, commands and guardrails.
sdk AGENTS.md
Instructions for zapier/sdk, covering agents.md, what this repo is, files to read before you start, when to use this sdk vs. alternatives and setup.