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 commands/1mcp-app/agent/indexgit clone --depth 1 https://github.com/1mcp-app/agentWhat 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 | $0.00032 | $0.02336 |
| Opus 5 | $0.00016 | $0.01168 |
| Sonnet 5 | $0.00006 | $0.00467 |
| Haiku 4.5 | $0.00003 | $0.00234 |
Grade A, and why
index 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 2d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command Reference
This section is the CLI lookup entrypoint. Use it when you already know which command family you need and want exact syntax, options, or examples.
For AI agents, the preferred path is CLI mode: keep MCP behind 1mcp serve, then use instructions, inspect, and run as a progressive-disclosure workflow instead of exposing a broad tool surface directly in the agent loop.
If you are still trying to get a first setup working, use Quick Start before drilling into command details.
Quick Reference
Main Commands
serve- Start the 1MCP server (default command)proxy- Start STDIO proxy to connect to running 1MCP HTTP serverinstructions- Show the CLI playbook and current server inventoryinspect- List exposed servers or inspect a tool schemarun- Call a tool through a running 1MCP servercli-setup- Install Codex or Claude bootstrap hooks and startup docsauth- Manage authentication profiles for secured serverstarget- Manage verified Runtime Target Contextsadmin- Manage CLI Admin sessions for Runtime Target Contextsapp- Manage desktop application MCP configurationsmcp- Manage MCP server configurationspreset- Manage server presets for dynamic filtering
Global Options
All 1MCP commands support the following global options:
--help, -h- Show help information--version- Show version information--config, -c <path>- Specify configuration file path--config-dir, -d <path>- Path to the config directory--cli-session-cache-path <path>- Path template for therun/inspectCLI session cache file; supports{pid}and{scope}
Environment Variables: All global options can be set via environment variables with the ONE_MCP_ prefix:
ONE_MCP_CONFIG=/path/to/config.jsonONE_MCP_CONFIG_DIR=/path/to/config/dirONE_MCP_CLI_SESSION_CACHE_PATH=/tmp/1mcp/.cli-session.{pid}
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.
- 2d ago First seen · 235 lines · 32 tokens per session scan A 7e54c6cb9439
index is a command published in the GitHub repository 1mcp-app/agent (494 stars, last pushed 3d ago), licensed Apache-2.0. It adds 32 tokens to every session and 2,336 once invoked, about $0.0002 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.
Other commands, from other repositories
go
MCP tool management and workflow proxy.
strict-development-rules
These rules apply strictly to all code modifications and additions within the Gemini CLI project.
frontend
Injects context of all relevant cli files.
find-docs
Find relevant documentation and output GitHub URLs.
full-context
Injects context of all relevant cli files.
introspect
Analyze the influence of system instructions on a specific action.