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/asyrjasalo/dynamic-mcp/agents-mdgit clone --depth 1 https://github.com/asyrjasalo/dynamic-mcpWrote 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/asyrjasalo/dynamic-mcp/agents-md)<a href="https://agentmods.dev/instructions/asyrjasalo/dynamic-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/asyrjasalo/dynamic-mcp/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 5.1 | $0.00780 | $0.00780 |
| Opus 5 | $0.00390 | $0.00390 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
dynamic-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 6d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dynamic-mcp Knowledge Base
Generated: 2026-02-14 Commit: addab19 Branch: main
Overview
MCP proxy server written in Rust that reduces LLM context overhead by grouping tools from multiple upstream MCP servers and loading tool schemas on-demand.
- Language: Rust 1.75+ (edition 2021)
- MCP SDK: rmcp v0.12
- Transports: stdio, HTTP, SSE
- Distributions: Binary (crates.io) + Python wheel (PyPI via maturin)
Structure
./
├── src/ # Rust source (auth, cli, config, proxy, server, watcher)
├── tests/ # Integration tests (8 files, ~120 tests)
├── docs/implementation/ # Architecture, status, testing docs
├── benches/ # Performance benchmarks
├── examples/ # Example config files
├── Cargo.toml # Binary + benchmark targets
└── pyproject.toml # Python wheel config
Code Map
| Symbol | Type | Location | Refs | Role |
|---|---|---|---|---|
| main | fn | src/main.rs | - | CLI entry point |
| serve | fn | src/server.rs | - | MCP server core |
| run_import | fn | src/cli/import_enhanced.rs | - | Import command |
| load_config | fn | src/config/loader.rs | - | Config loading |
Where to Look
| Task | Location | Notes |
|---|---|---|
| Config schema | src/config/schema.rs | JsonSchema generation |
| OAuth flow | src/auth/ | OAuth2 client + token store |
| MCP proxy | src/proxy/ | Client, transport, types |
| CLI commands | src/cli/ | Import, config parsing |
| Tests | tests/ | Integration tests |
| Benchmarks | benches/performance.rs | Performance tests |
Conventions
- Formatting:
cargo fmt(default rustfmt) - Linting:
cargo clippy -- -D warnings(warnings = errors) - Tests: Unit tests inline (
#[cfg(test)]), integration intests/ - Naming:
test_<category>_<feature>_<scenario> - TDD: Write failing tests BEFORE implementation
- Docs: Update CHANGELOG.md, STATUS.md, TESTING.md after changes
Anti-Patterns (This Project)
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.
- 6d ago First seen · 101 lines · 780 tokens per session scan A 267feff5fced
dynamic-mcp AGENTS.md is an instructions file published in the GitHub repository asyrjasalo/dynamic-mcp (11 stars, last pushed 5mo ago), licensed MIT. It adds 780 tokens to every session, about $0.0039 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
claude-tap AGENTS.md
Instructions for liaohch3/claude-tap, covering maintainer automation notes, agents 索引, documentation boundary, review guidelines and pre-commit hook.
hoop CLAUDE.md
Claude Code instructions for hoophq/hoop, covering claude.md, project overview, toolchain & prerequisites, architecture and module breakdown.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Claude Code instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
mistral-mcp CLAUDE.md
Instructions for Swih/mistral-mcp, covering claude.md — mistral-mcp, 1. identité du projet, 2. règles dures (ne pas transgresser), 3. layout & responsabilités and 4. conventions de code.
aiterm-mcp AGENTS.md
AGENTS.md instructions for kitepon/aiterm-mcp, covering agents.md, 製品と所有境界, 現行契約, コード所有 and 作業規律.