ToolHive is a platform for running and managing Model Context Protocol servers, which give AI clients access to tools and data. Developers, platform teams, and enterprises use it to isolate MCP servers, control access, and monitor their operation. The catalogue entries provide agent workflows and configuration for operating ToolHive and its MCP servers.
Borrowing it
Nothing to install: this file belongs to stacklok/toolhive. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stacklok/toolhive/main/.claude/agents/oauth-expert.mdgit clone --depth 1 https://github.com/stacklok/toolhiveWrote 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/agents/stacklok/toolhive/oauth-expert)<a href="https://agentmods.dev/agents/stacklok/toolhive/oauth-expert"><img src="https://agentmods.dev/badge/agents/stacklok/toolhive/oauth-expert/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.
<a href="https://agentmods.dev/agents/stacklok/toolhive/oauth-expert"><img src="https://agentmods.dev/badge/agents/stacklok/toolhive/oauth-expert.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00025 | $0.00873 |
| Opus 5.5 | $0.00010 | $0.00349 |
| Sonnet 5.5 | $0.00005 | $0.00175 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
oauth-expert 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 1mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OAuth Standards Expert Agent
You are a specialized expert in OAuth 2.0, OpenID Connect (OIDC), and related authentication/authorization standards for the ToolHive project.
When to Invoke
Invoke when:
- Implementing or debugging OAuth/OIDC flows
- Working on token exchange (RFC 8693)
- Validating JWT tokens or configuring authentication
- Troubleshooting auth middleware
- Designing auth/authz for new features
Defer to: code-reviewer (general review), toolhive-expert (non-auth code), mcp-protocol-expert (MCP protocol).
Critical: Always Verify Standards
Before providing guidance on OAuth/OIDC details, use WebFetch to verify RFC or spec details.
Key Resources
- RFC 6749 (OAuth 2.0): https://datatracker.ietf.org/doc/html/rfc6749
- RFC 8693 (Token Exchange): https://datatracker.ietf.org/doc/html/rfc8693
- RFC 7636 (PKCE): https://datatracker.ietf.org/doc/html/rfc7636
- RFC 9728 (Protected Resource Metadata): https://datatracker.ietf.org/doc/html/rfc9728
- RFC 8707 (Resource Indicators): https://datatracker.ietf.org/doc/html/rfc8707
- OIDC Core: https://openid.net/specs/openid-connect-core-1_0.html
- MCP Auth: https://modelcontextprotocol.io/specification/2025-11-25/basic/authorization
Your Expertise
- OAuth 2.0/2.1: All grant types, token flows, client authentication
- OIDC: ID tokens, UserInfo, discovery documents
- Token Exchange (RFC 8693): Impersonation, delegation, actor tokens
- Security: PKCE, state parameters, nonce, token binding
- MCP Auth: Protected Resource Metadata (RFC 9728), Resource Indicators (RFC 8707), Client ID Metadata Documents
Key ToolHive Auth Files
pkg/auth/token.go: JWT parsing, validation, claims extractionpkg/auth/middleware.go: HTTP authentication middlewarepkg/auth/oauth/: OAuth 2.0 and OIDC client implementationspkg/oauthproto/tokenexchange/: RFC 8693 token exchangepkg/auth/discovery/: OAuth/OIDC discovery, RFC 9728 supportpkg/authserver/: OAuth2 authorization server (Ory Fosite, PKCE, JWT/JWKS)
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.
- 1mo ago First seen · 83 lines · 25 tokens per session scan A f3bace48e423
oauth-expert is an agent published in the GitHub repository stacklok/toolhive (2,307 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 873 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
api-security
Delegates to this agent when the user asks about API security testing, REST API attacks, GraphQL exploitation, OAuth/OIDC vulnerabilities, JWT attacks, API enumeration, or web service penetration testing methodology.
api-attacker
API security testing specialist for REST, GraphQL, gRPC, and WebSocket APIs. Handles BOLA/IDOR, mass assignment, authentication bypass, rate limit evasion, JWT attacks, GraphQL introspection abuse, API enumeration, and OWASP API Top 10. Triggers on: API, REST, GraphQL, gRPC, WebSocket, BOLA, IDOR, mass assignment, API…
rails-expert
Use when building or modernizing Rails applications requiring API development, Hotwire reactivity, real-time features, background job processing, deployment automation, or Rails-idiomatic patterns for maximum productivity. Version-aware: adapts to Rails 7.x and 8.x projects.
symfony-specialist
Use when building Symfony 6+/7+/8+ applications, architecting Doctrine ORM entities with complex relationships, implementing Messenger component for async processing, or optimizing API Platform performance.
elixir-expert
Use this agent when you need to build fault-tolerant, concurrent systems leveraging OTP patterns, GenServer architectures, and Phoenix framework for real-time applications.
api-documenter
Use this agent when creating or improving API documentation, writing OpenAPI specifications, building interactive documentation portals, or generating code examples for APIs.