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/oztamir/mcplexer/agents-mdgit clone --depth 1 https://github.com/OzTamir/mcplexerWhat 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 | $0.00729 | $0.00729 |
| Opus 5 | $0.00365 | $0.00365 |
| Sonnet 5 | $0.00146 | $0.00146 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
mcplexer 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 yesterday.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCPlexer Agent Guide
Project purpose
MCPlexer is a lightweight stdio MCP proxy. It lets users run multiple labeled instances of the same upstream MCP server by rewriting exposed tool names and descriptions while forwarding calls to the original upstream tool.
Example behavior:
- upstream tool:
get-calendar-events - exposed tool:
personal:get-calendar-events - forwarded call:
personal:get-calendar-events-> upstreamget-calendar-events
Commands
Use pnpm for package management.
- Install:
pnpm install - Lint/format check:
pnpm lint - Typecheck:
pnpm typecheck - Test:
pnpm test - Build:
pnpm build
Do not run a dev server; this is a CLI/MCP stdio utility.
Architecture map
src/cli.ts: executable boundary, error-to-exit handling.src/config.ts: public CLI parse orchestration.src/raw-cli.ts: raw argv tokenization and option parsing.src/upstream-config.ts: stdio/remote upstream and header config shaping.src/config-types.ts: shared config types and usage errors.src/prefix.ts: pure tool-name and description rewrite helpers.src/upstream.ts: upstream MCP client connection logic for stdio, Streamable HTTP, and SSE.src/transport-adapter.ts: compatibility adapter for MCP SDK transport typing underexactOptionalPropertyTypes.src/proxy.ts: downstream stdio MCP server handlers fortools/listandtools/call.tests/fixtures/echo-mcp.mjs: real upstream MCP fixture for smoke/manual protocol checks.
Invariants
- MCPlexer itself always speaks stdio to the downstream client.
- Local upstream MCPs are launched with
-- <command> [args...]and inherit the wrapper environment. - Remote upstream MCPs use
--url;autotries Streamable HTTP first, then SSE. - Remote OAuth auth must use the MCP SDK
authProviderpath, not hand-builtAuthorizationheaders. - Browser OAuth must keep auth URLs and callback status on stderr or the browser response; stdout stays MCP JSON-RPC only.
- Listed tools must preserve upstream metadata except
nameanddescription. tools/callmust reject names that do not start with the configured prefix plus separator.tools/callmust strip only the configured prefix before calling upstream.- Keep prefixing behavior pure and testable in
src/prefix.ts. - Validate untrusted CLI input at the boundary; do not pass raw argv deeper than
src/raw-cli.ts.
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.
- yesterday First seen · 70 lines · 729 tokens per session scan A 3cfb94a88543
mcplexer AGENTS.md is an instructions file published in the GitHub repository OzTamir/mcplexer (1 stars, last pushed 2mo ago), licensed MIT. It adds 729 tokens to every session, about $0.0036 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.