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/joshrotenberg/mcp-proxy/agents-mdgit clone --depth 1 https://github.com/joshrotenberg/mcp-proxyWrote 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/joshrotenberg/mcp-proxy/agents-md)<a href="https://agentmods.dev/instructions/joshrotenberg/mcp-proxy/agents-md"><img src="https://agentmods.dev/badge/instructions/joshrotenberg/mcp-proxy/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 | $0.01805 | $0.01805 |
| Opus 5 | $0.00903 | $0.00903 |
| Sonnet 5 | $0.00361 | $0.00361 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
mcp-proxy 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 4d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Overview
mcp-proxy is a config-driven MCP (Model Context Protocol) reverse proxy built in Rust. It aggregates multiple MCP backends behind a single HTTP endpoint with per-backend middleware, authentication, and observability. Built on tower-mcp and the tower middleware ecosystem.
Package name: mcp-proxy. Binary name: mcp-proxy. Library name: mcp_proxy.
Project structure
src/
main.rs # CLI entry point (clap), logging setup
lib.rs # Library root, re-exports Proxy and ProxyConfig
proxy.rs # Core: builds proxy, middleware stack, and axum router
config.rs # TOML config parsing, all config types
admin.rs # HTTP admin API (/admin/backends, /admin/health, etc.)
admin_tools.rs # MCP admin tools (proxy/ namespace, via ChannelTransport)
reload.rs # Hot reload: file watcher, dynamic backend addition
test_util.rs # MockService, ErrorMockService, call_service helper
# Global middleware (wraps the entire proxy, applied in proxy.rs)
access_log.rs # Structured access logging (AccessLogService, target: mcp::access)
alias.rs # Tool renaming (AliasService)
filter.rs # Capability filtering -- allow/deny lists, glob patterns (CapabilityFilterService)
inject.rs # Argument injection into tool calls (InjectArgsService)
mirror.rs # Traffic mirroring to canary backends (MirrorService)
cache.rs # Response caching with TTL (CacheService)
coalesce.rs # Request deduplication (CoalesceService)
validation.rs # Argument size limits (ValidationService)
metrics.rs # Prometheus counters and histograms (MetricsService)
rbac.rs # Role-based access control (RbacService)
token.rs # Auth token passthrough to backends (TokenPassthroughService)
# Per-backend middleware (applied per-backend in proxy.rs and reload.rs)
retry.rs # Retry with exponential backoff (McpRetryPolicy)
outlier.rs # Outlier detection and ejection (OutlierDetectionLayer)
tests/
integration.rs # Middleware composition tests with in-process backends via ChannelTransport
e2e.rs # Comprehensive E2E test suite (44 tests, 10 tiers)
examples/
*.toml # Example proxy configs for different deployment patterns
docker-compose/ # Docker compose example with HTTP backend
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.
- 4d ago First seen · 174 lines · 1,805 tokens per session scan A a186886c1c98
mcp-proxy AGENTS.md is an instructions file published in the GitHub repository joshrotenberg/mcp-proxy (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,805 tokens to every session, about $0.0090 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
rustunnel CLAUDE.md
Claude Code instructions for joaoh82/rustunnel, covering claude.md, what is rustunnel, parent project, how i fit in and common commands.
rustunnel AGENTS.md
AGENTS.md instructions for joaoh82/rustunnel, covering agents.md, using rustunnel as a tool (expose local services), one-time setup the user must do and what you can do (mcp tools).
greptimedb AGENTS.md
AGENTS.md instructions for GreptimeTeam/greptimedb, covering agents.md, core commands, repo map, read before changing code and high-signal entry points.
zentinel AGENTS.md
AGENTS.md instructions for zentinelproxy/zentinel, covering zentinel, philosophy (north star), architecture, crates and core crates.
void-box AGENTS.md
AGENTS.md instructions for the-void-ia/void-box, covering agents.md — voidbox, design proposals: rfc + adr process, code intelligence, commit and pr messages and markdown documentation style.
void-box CLAUDE.md
Claude Code instructions for the-void-ia/void-box, covering claude.md and claude-specific guidance.