INVARA MCP server
io.github.Jujitae/invara·v0.3.0·1 starsIndependent verification that a change kept its declared constraints. No model in the verdict path.
1 stars33 downloads/wk
Reviews
Write oneNobody has reviewed INVARA yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
INVARA tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.10 · 2026-10-14 · same rubric, same numbers if you re-run it
- Code scan37 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 34 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How INVARA compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 88/100
- higher than 80% of 4,460 AI and agents servers
- GitHub stars
- 1
- more than 50% of 2,711 AI and agents servers
- Downloads a week
- 33
- more than 22% of 1,538 AI and agents servers with a package
Install INVARA in Claude Code, Cursor or VS Code
claude mcp add invara -- uvx invara
What the publisher says
From the INVARA repository's README, as published. We do not edit it. Read it on GitHub
<!-- mcp-name: io.github.Jujitae/invara -->
INVARA
Engineering invariants for AI-built software.
INVARA works with Claude Code, Codex, and any coding agent that can use a shell. It verifies declared constraints against observable evidence; it does not prove software correctness.
seal before work -> agent does the work -> judge
|
PASS / BLOCK / UNVERIFIABLE / HUMAN_REVIEWStart with the path that matches your environment:
/plugin marketplace add Jujitae/invara, then /plugin install invara.
- Claude Code: install the bundled editor/plugin experience with
uvx --from invara==0.3.0 invara list, or install persistently with python -m pip install invara==0.3.0.
- Codex or another shell-capable agent: run
AI Agent Quickstart, then preserve the exact verdict it receives.
- Tell your agent: use the copy-paste instructions in
The first result is a verdict, not an agent self-report. PASS means every declared check returned what it promised and protected paths stayed unchanged. BLOCK, UNVERIFIABLE, and HUMAN_REVIEW stay exactly that; none is success by reinterpretation.
Current public release: 0.3.0. Status: Alpha. INVARA Free is distributed publicly; INVARA Pro is a separate paid product. INVARA is not autonomous authorization and not an enterprise compliance control.
Transformation assurance in 0.3.0, Gen 1
Two local CLI workflows can now check a declared behavior envelope around a refactor or migration:
Manifest and can search for a minimized counterexample.
- invara assure compares an existing before/after pair under an Equivalence
after the declared checks accept it.
- invara repair governs a repair one unit at a time, keeping a unit only
Gen 1 measures only the inputs, observations, policies, and claims declared in the manifest. A PASS is bounded to that envelope; it is not a general proof of correctness, security, or bug-free software. The workflows run user-named commands with the user's permissions. They make no outbound network call; an HTTP probe may connect only to a loopback service that the manifest starts for the session.
Start with the CLI guide and the manifest guide. Synthetic examples and display reports are under fixtures/ and docs/transformation-assurance/samples/.
What this is not
Read this part before the install line. It is short on purpose, and the word that carries the promise above is verifiable — not correct.
INVARA does not prove software correctness.
It verifies declared constraints against observable evidence.
Specifically:
good, whether the architecture holds, or whether the tests are the right tests. Stack a new floor on junk and, if this floor was built to the declared spec, the verdict is PASS.
- It does not inspect your codebase. It never asks whether the code is
strong as your suite. INVARA reports the exit code; it does not have an opinion about coverage.
- It does not find bugs. A completion check that runs your suite is only as
contract. A weak contract earns a weak PASS, and the contract is stored verbatim so anyone can see how weak it was.
- It does not decide what should have been promised. You write the
your permissions. Do not seal a contract you have not read.
- It is not a sandbox. Completion checks are commands and they run with
work matched it. The checks are what bind.
- It does not judge intent. intent is prose; nothing checks that the
no model anywhere in the verdict path.
- It is not an AI code generator and not an LLM code-review bot. There is
The narrow claim, which is what the machine actually does:
It decides, independently, whether this change kept the promises it made.
CLI first verdict, in more detail
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
INVARA: common questions
- Is INVARA MCP server safe?
- Yes, by our scan: it is graded A (88/100). Read the INVARA safety report
- How do I install INVARA?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does INVARA need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is INVARA maintained?
- The last commit was 54 days ago (2026-09-11). The latest release is v0.3.0.
- What can I use instead of INVARA?
- Servers from other publishers that do the same job: Power BI Authoring MCP Server (Local).
- How does INVARA compare with other AI and agents MCP servers?
- safety score 88/100 (higher than 80% of 4,460 AI and agents servers); github stars 1 (more than 50% of 2,711 AI and agents servers); downloads a week 33 (more than 22% of 1,538 AI and agents servers with a package). Full comparison.
Alternatives to INVARA
Same job from other publishers: the closest match first, then the best rated.
- Power BI Authoring MCP Server (Local)The Power BI Authoring MCP server lets an AI agent create and change Power BI semantic models.not reviewedEstablishedA