2 findingsStatic scanned
Adds Storybook component and story documentation tools to an MCP server you run yourself.
9.4M installs/moMIT
Iris Eval MCP Server
iris-eval · MCP server
Your AI agent logs its runs as traces with spans, tool calls, token use and cost by calling its tool, or your code posts them over HTTP, and each output is scored against built-in rules for completeness, relevance, safety and cost or against custom rules you deploy. Twelve tools also compare two runs, verify citations and score outputs with an LLM judge using your own Anthropic or OpenAI key. Traces are stored in a local SQLite database, with a web dashboard to browse them. Suits people checking agent quality during development.
Written by ooruby from the README of @iris-eval/mcp-server 0.20.0.
Not claimed by its maker. Is this yours? Prove it and answer the findings
Why it's useful
You can see what your agent did, what it cost and whether its output passed your rules, rather than judging runs by eye.
What you could do with it
- Log an agent run with its tool calls, token use and cost, and score the output in the same call.
- Check an output for personal data such as card numbers or API keys, and for prompt injection.
- Compare two runs of stored evaluations to see whether a change made your agent worse.
Written from its documentation: what it says it can do, not what our checks found.
Maintenance
Not measuredNo release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.
Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured
What this does not cover
- Everything. Treat it as you would software from anywhere else.
Receipt history: every signed receipt for every version of this listing, and what changed between them.
In its maker's words
Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.
Compare with
Compare all 4How far this has been checked
Static scanned
- What it establishes
- Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
- What it does not
- How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
- Exactly what was read
- Version 0.20.0, the file with digest sha512-BXwsjN/+prNMy71OV2lgHvwkXYnuk5Sz7mcyTrxEp5jyj5d61gJJQvPoCDYSz+7haRO76AL/FeuUOABYegGCvw==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
- Authentication
- Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
Adding it
Paste this into your client's MCP configuration.
{
"mcpServers": {
"iris-mcp": {
"command": "npx",
"args": [
"-y",
"-p",
"@iris-eval/mcp-server@0.20.0",
"iris-mcp"
]
}
}
}Or run it directly.
npx -y -p @iris-eval/mcp-server@0.20.0 iris-mcpPinned to 0.20.0, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.
Where this came from
- Registry
- npm
- Package
- @iris-eval/mcp-server
- Version read
- 0.20.0
- Resolved
- 2026-10-10
Built from source, attested
npm publishes a signed statement that this exact package was built from the repository below, at this commit. It is verifiable without taking our word for it.
- Repository
- github.com/iris-eval/mcp-server
- Commit
- 78453df397ad
- Built by
- github.com/actions/runner/github-hosted
- Registry publish attestation
- signed by npm · 2026-10-10
- Checked
- 2026-10-10
The badge, if this is your listing
It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.
[](https://ooruby.com/market/iris-eval-mcp-server)About this listing
- Kind
- MCP server
- Category
- Developer tools
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-04
Similar MCP servers
All MCP serversVerification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.