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 agents/argos-ci/docs/mcp-servergit clone --depth 1 https://github.com/argos-ci/docsWhat 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 | $0.00027 | $0.01474 |
| Opus 5 | $0.00014 | $0.00737 |
| Sonnet 5 | $0.00005 | $0.00295 |
| Haiku 4.5 | $0.00003 | $0.00147 |
Grade A, and why
mcp-server 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP server
Connect your AI tools to Argos using the Model Context Protocol (MCP), an open standard that lets AI assistants interact with your Argos projects.
MCP defines a common way for an AI assistant to discover the tools a service exposes and call them on your behalf. Instead of a bespoke plugin for each assistant, a service publishes one MCP server, and every MCP-compatible client — Claude, Cursor, VS Code, and others — can use it.
What is the Argos MCP server?
The Argos MCP server is the official remote MCP server for Argos, available at:
https://mcp.argos-ci.com
It integrates with popular AI assistants like Claude, enabling them to:
- List builds and inspect their screenshot diffs
- Approve or reject builds, dismiss reviews, and request reviewers
- Read and post comments on builds and tests
- Investigate flaky tests and ignore the changes behind them
- Read and update project settings, contributors, deployments, and automation rules
- Manage a team's members, invites, and email domains
- Retrieve project metadata, account analytics, plan, and usage
- Upload standalone images and videos and get shareable links for them
The server is remote and uses the streamable HTTP transport — there is no package to install or process to run locally. Configure your client with the transport http (sometimes labeled streamable-http) and the URL above. It implements the latest MCP Authorization and Streamable HTTP specifications.
Available tools
Tools are generated directly from the Argos REST API: every API operation that a user can call is exposed as an MCP tool with the same name, parameters, and permissions. When the API gains an endpoint, the MCP server gains the matching tool — with no client update on your side.
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 · 144 lines · 27 tokens per session scan A 735c250494cf
mcp-server is an agent published in the GitHub repository argos-ci/docs (5 stars, last pushed 14d ago), licensed MIT. It adds 27 tokens to every session and 1,474 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 2026-08-31.
Other agents, from other repositories
docs
READMEs, API references, architecture notes, changelogs, and inline comments — written for the person who arrives without context.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
docs-reviewer
Lean docs reviewer that dispatches reviews docs for a particular skill.