proxy

A bridge that lets software using the standard input/output interface connect to a running 1MCP server over HTTP. 1MCP is a runtime that exposes tools from connected services to an AI agent.

In plain words
What is it for?
It helps connect an AI client to a running 1MCP runtime, apply presets or tags to the available tools, and expose the selected tool set through a compatible local interface.
Why use it?
It connects clients that understand local standard input/output but do not directly support HTTP-based MCP connections. It can also preserve project settings while selecting which tools are exposed.

Command

Install

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.

agentmods
npx agentmods add commands/1mcp-app/agent/proxy
Clone the repo
git clone --depth 1 https://github.com/1mcp-app/agent
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,413 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.01413
Opus 5 $0.00012 $0.00707
Sonnet 5 $0.00005 $0.00283
Haiku 4.5 $0.00002 $0.00141

Measured yesterday against content hash 20f4f5827df2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

proxy 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.

docs/en/commands/proxy.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proxy Command

1mcp proxy is the maximum-compatibility bridge on top of a running 1MCP runtime.

It connects a local stdio transport to a running 1mcp serve HTTP runtime. In practice, this is the preferred fallback after CLI mode because most AI clients already support stdio, while fewer support streamable HTTP, SSE, or CLI mode.

Choose the Right Path

1MCP supports three different paths:

  1. CLI mode for agent loops: recommended for Codex, Claude, and similar agent sessions.
  2. proxy: recommended when you want the broadest client compatibility while keeping project context.
  3. Direct streamable HTTP MCP attachment: use when the client can connect directly and you do not need project context.

proxy is not the main product experience. CLI mode remains the first choice for agent loops. proxy exists as the best non-CLI path when you want stdio compatibility plus .1mcprc and template-server support.

Synopsis

1mcp proxy [options]

What proxy Does

  • discovers a running 1mcp serve instance
  • forwards stdio MCP traffic to that runtime over HTTP
  • can apply preset, filter, or tags selection before exposing the bridged inventory

The runtime still lives in serve. proxy does not replace it.

Auto-Discovery

proxy can discover a running runtime in these ways:

  1. user-supplied --url
  2. PID-file-based discovery
  3. localhost port scan fallback

If project config is present, proxy can also merge settings from .1mcprc.

Project Configuration with .1mcprc

.1mcprc is useful when you repeatedly bridge the same project or client to the same preset or filtered runtime view.

Example:

{
  "preset": "development"
}

Priority order is:

  1. command-line options
  2. .1mcprc
  3. defaults

Common Options

Connection

  • --url, -u <url>: Override runtime auto-discovery.
  • --context <name>: Use a named Runtime Target Context, including its saved bearer token when present.
  • --config-dir, -d <path>: Use a specific config directory during discovery.

Read the full file on GitHub · 182 lines

Changes

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.

  1. yesterday First seen · 182 lines · 23 tokens per session scan A 20f4f5827df2

Subscribe to this mod's changes

proxy is a command published in the GitHub repository 1mcp-app/agent (494 stars, last pushed 3d ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,413 once invoked, about $0.0001 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.