Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.ets-public/brevi

PYPI · BREVI · 2 COMPONENTS

Build and run plain Python as fast native programs: check, run, test and patch tools for agents.

+3 this week 83 Trust /100

Last scanned (23 hours ago)

Scores higher than 83% of PyPI servers

Category Developer Tools

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to ets-public/brevi). View diagnostics → Pass
  • Clear OSI-approved license (Apache-2.0).Pass
  • Actively maintained (last published 1 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability51
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 2063 tokens (~257/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management50
  • Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage90
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 69% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 0
    • Package version: 0.28.2 → 0.28.3 functional
  • 17 Nov 26 +16
    • Malware scan: unverified → pass ▲ security
  • 16 Nov 26 0
    • Malware scan: unverified → pass ▲ security
    • Package version: 0.28.0 → 0.28.2 functional
    • Package version: 0.28.0 → 0.28.1 functional
  • 15 Nov 26 −14
    • Malware scan: pass → unverified ▼ security
    • Package version: 0.27.1 → 0.28.0 functional
  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Nov 26 0
    • Schema quality: 210 → 247 ▼ functional
    • Package version: 0.26.0 → 0.27.1 functional
  • 10 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed pypi/brevi@0.28.3

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem pypi
Reason Verified
Discovered via Registry attestation endpoint
Source repo ets-public/brevi
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/ets-public/brevi/.github/workflows/release.yml@refs/heads/main
Rekor log index 3992457062
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:b9d336e8aeb9987aff4f8f5fc165459a54b9b81715dda4a4baed6dcbed6c8703

Background: How many MCP packages publish verified provenance →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 8 exposed · ~1,908 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
check ~290

Compile without running. OK or one JSON error per line: {line, msg, fix}. The server keeps the program: pass code once, then omit it and change it with patch or edit.

NameTypeReqDescription
allowarray–Capabilities granted under the sandbox, within what the server allows (brevi mcp --allow ...); an allow line in the code grants nothing
allow_netarray–Hosts the program may reach under the sandbox (api.example.com); allow net grants every host
allow_pyarray–Python libraries CPython may run under the sandbox (requests, pydantic)
allow_readarray–Folders or files the program may read under the sandbox (relative to where brevi mcp started); allow read grants every file
allow_writearray–Folders or files the program may write under the sandbox; allow write grants every file
codestring–Plain Python
fastboolean–Only Brevi's own checks, without rustc
filestring–Default main.py; other files are modules it imports (util.py for import util)
fixboolean–Apply every suggested fix to the kept program
sandboxboolean–Default true: files, native code and Python libraries need allow or allow_py. false is refused unless the server was started with --trust-calls

No output schema declared.

No examples provided.

edit ~251

Replace lines from..to (1-based, inclusive) of the kept program with text (empty text deletes; to = from - 1 inserts before from). Then checks like patch.

NameTypeReqDescription
allowarray–Capabilities granted under the sandbox, within what the server allows (brevi mcp --allow ...); an allow line in the code grants nothing
allow_netarray–Hosts the program may reach under the sandbox (api.example.com); allow net grants every host
allow_pyarray–Python libraries CPython may run under the sandbox (requests, pydantic)
allow_readarray–Folders or files the program may read under the sandbox (relative to where brevi mcp started); allow read grants every file
allow_writearray–Folders or files the program may write under the sandbox; allow write grants every file
filestring––
fromintegeryes–
sandboxboolean–Default true: files, native code and Python libraries need allow or allow_py. false is refused unless the server was started with --trust-calls
textstringyes–
tointegeryes–

No output schema declared.

No examples provided.

guide ~175

The Brevi language guide. Not needed to start: write plain Python (a .py file) and Brevi builds it to native code, which runs plain loops several times faster than CPython (typed build: 1.6x to 37.9x, median 9.3x, on our 12 compute benchmarks; only a small share of CPython's own test programs take the typed build, and when values change type it falls back to the dynamic build, median 0.85x), so write the plain, direct solution and do not hand-optimise it. Ask with a word (sections: Strings, Lists, Python, Libraries) for only the lines about it, e.g. when a build error names something; with no word, the whole core.

NameTypeReqDescription
wordstring––

No output schema declared.

No examples provided.

patch ~243

Replace each def or class in patch by name in the kept program (or add it); del def name removes one. Then checks: prints what changed and OK or the errors.

NameTypeReqDescription
allowarray–Capabilities granted under the sandbox, within what the server allows (brevi mcp --allow ...); an allow line in the code grants nothing
allow_netarray–Hosts the program may reach under the sandbox (api.example.com); allow net grants every host
allow_pyarray–Python libraries CPython may run under the sandbox (requests, pydantic)
allow_readarray–Folders or files the program may read under the sandbox (relative to where brevi mcp started); allow read grants every file
allow_writearray–Folders or files the program may write under the sandbox; allow write grants every file
codestring––
filestring––
patchstringyes–
sandboxboolean–Default true: files, native code and Python libraries need allow or allow_py. false is refused unless the server was started with --trust-calls

No output schema declared.

No examples provided.

run ~396

Compile and run the kept program (or code, plain Python). With cases, runs each and prints ok or the first differing line. Plain Python is checked (verify, on by default): under the sandbox the typed build against Brevi's dynamic build, with sandbox false against CPython. The last line says identical, or the output is the reference's when Brevi's typed answer differs.

NameTypeReqDescription
allowarray–Capabilities granted under the sandbox, within what the server allows (brevi mcp --allow ...); an allow line in the code grants nothing
allow_netarray–Hosts the program may reach under the sandbox (api.example.com); allow net grants every host
allow_pyarray–Python libraries CPython may run under the sandbox (requests, pydantic)
allow_readarray–Folders or files the program may read under the sandbox (relative to where brevi mcp started); allow read grants every file
allow_writearray–Folders or files the program may write under the sandbox; allow write grants every file
argsarray––
casesarray––
codestring––
filestring––
limitsobject–Resource limits on the program run (not the build); the program is stopped at the first one it reaches
sandboxboolean–Default true: files, native code and Python libraries need allow or allow_py. false is refused unless the server was started with --trust-calls
stdinstring––
timeoutinteger–Seconds for build and run (default 20; per case 10)
verifyboolean–Default true: check the answer and give the reference's output if they differ (under the sandbox, which cannot hold CPython, against Brevi's dynamic build; with sandbox false, against CPython)

No output schema declared.

No examples provided.

show ~44

The kept program, or lines from..to of it, with line numbers.

NameTypeReqDescription
filestring––
frominteger––
tointeger––

No output schema declared.

No examples provided.

test ~252

Run the test blocks of the kept program (or code).

NameTypeReqDescription
allowarray–Capabilities granted under the sandbox, within what the server allows (brevi mcp --allow ...); an allow line in the code grants nothing
allow_netarray–Hosts the program may reach under the sandbox (api.example.com); allow net grants every host
allow_pyarray–Python libraries CPython may run under the sandbox (requests, pydantic)
allow_readarray–Folders or files the program may read under the sandbox (relative to where brevi mcp started); allow read grants every file
allow_writearray–Folders or files the program may write under the sandbox; allow write grants every file
codestring––
filestring––
limitsobject–Resource limits on the program run (not the build); the program is stopped at the first one it reaches
sandboxboolean–Default true: files, native code and Python libraries need allow or allow_py. false is refused unless the server was started with --trust-calls
timeoutinteger–Seconds (default 20)

No output schema declared.

No examples provided.

verify ~257

Proof the native build answers as CPython does: builds the kept program (or code, plain Python) natively, runs it and python3 on each input, and compares stdout, exit code and stderr (CPython runs twice, so output that changes run to run is reported, not certified). One JSON line per input, then a certificate {verify: identical, differs, unstable, timeout, limit or not built; sha256, path, speedup}. Runs CPython on the code, which the sandbox cannot hold, so it needs sandbox false (a server started with --trust-calls); run checks sandboxed code against Brevi's dynamic build instead.

NameTypeReqDescription
argsarray––
codestring–Plain Python
filestring––
inputsarray–stdin for each run (default one run, empty stdin)
limitsobject–Resource limits on the program run (not the build); the program is stopped at the first one it reaches
onceboolean–Run CPython once, not twice
sandboxboolean–Must be false: verify runs python3 on the code
timeoutinteger–Seconds for each run (default 20)

No output schema declared.

No examples provided.

Install

How do I install the io.github.ets-public/brevi MCP server?

io.github.ets-public/brevi runs locally as a PyPI package, launched with uvx brevi mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · brevi

# add to Claude Code
claude mcp add ets-public-brevi -- uvx brevi mcp
Common questions

What is the io.github.ets-public/brevi MCP server?

io.github.ets-public/brevi is an MCP server listed in the public MCP registry as io.github.ets-public/brevi. Build and run plain Python as fast native programs: check, run, test and patch tools for agents. This page covers its PyPI package (brevi).

Is the io.github.ets-public/brevi MCP server safe to use?

io.github.ets-public/brevi scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.ets-public/brevi MCP server expose?

io.github.ets-public/brevi exposes 8 tools: guide, check, run, test, patch, and 3 more. Their descriptions and schemas cost roughly 1,908 tokens of context every time the server is loaded.

Is the io.github.ets-public/brevi MCP server still maintained?

io.github.ets-public/brevi is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.ets-public/brevi MCP server under?

io.github.ets-public/brevi declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the io.github.ets-public/brevi MCP server?

VerifyMCP ran 16 checks on io.github.ets-public/brevi, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.