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/rungit 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 | $0.00030 | $0.01200 |
| Opus 5 | $0.00015 | $0.00600 |
| Sonnet 5 | $0.00006 | $0.00240 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
run 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Command
Call an MCP tool against a running 1MCP serve instance.
Synopsis
npx -y @1mcp/agent run <server>/<tool> [options]
Description
The run command is the execution step in the CLI workflow:
- Run
instructionsto see the playbook and available servers - Run
inspectto list tools and inspect tool schemas - Run
runto invoke the selected tool
run talks to a running 1mcp serve instance, forwards preset and tag filters, and prints tool output to stdout. Errors are written to stderr only so the command stays pipe-friendly.
run is intentionally the last step. The recommended flow is to discover broadly with instructions, narrow with inspect, confirm the exact tool schema with inspect <server>/<tool>, and only then invoke the tool.
Before a REST-to-MCP fallback, run checks the client-facing inspect status. A loading backend returns server_loading and 1mcp wait <server> rather than receiving an early MCP invocation. Failed or cancelled backends return server_unavailable; an OAuth-gated backend returns authorization guidance.
Options
Target and Discovery
<server>/<tool>- Tool reference in qualified form--url, -u <url>- Override auto-detected 1MCP server URL--context <name>- Use a named Runtime Target Context and its saved bearer token, if any--preset, -p <name>- Use a preset when calling the running server--tag-filter, -f <expression>- Apply an advanced tag filter expression--tags <tag>- Apply simple comma-separated tags
Input Options
--args <json>- Tool arguments as a JSON object
If --args is omitted and stdin is provided, run tries to map stdin automatically:
- If stdin is a JSON object, it is used as the tool arguments
- Otherwise, stdin is mapped into the first required string argument after schema inspection
Output Options
--format <toon|json|text|compact>- Output format--raw- Alias for--format json--max-chars <number>- Maximum characters for compact output (default:2000)
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 · 126 lines · 30 tokens per session scan A ca0d9c33108e
run is a command published in the GitHub repository 1mcp-app/agent (494 stars, last pushed 3d ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,200 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.
release-harn
Run the tag-first Harn release workflow.
harn-release
Run the tag-first Harn release workflow.
web-component
Create a new web component following the established project conventions.
send
Send a WhatsApp message using the wu MCP server.