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.

crit

PYPI · CRIT

Build, evaluate and serve a bespoke LLM inference engine for your own GPU with crit's commands.

Available components

−12 this week 63 Trust /100

Last scanned (14 hours ago)

Scores higher than 55% of PyPI servers

Category AI and Machine Learning

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 Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 2 of 25 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to crit-labs/crit). View diagnostics → Pass
  • Clear OSI-approved license (Apache-2.0).Pass
  • Actively maintained (last published 2 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability33
  • 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Fail
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 12725 tokens (~176/item across 72 items; 62 tools + 10 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 Management40
  • Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage96
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 88% of tool parameters carry a description.Partial
Tool Safety94
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 13 of 17 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "crit_eval_context" implies "eval" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
  • An AI judge read all 64 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (15)

  • 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

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain SecurityMalware scan not yet available for this package.

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 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 16 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.

  • 14 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 11 Nov 26 −14
    • Malware scan: pass → unverified ▼ security
  • 9 Nov 26 73

    First indexed and scored.

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/crit@0.17.2

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 crit-labs/crit
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/crit-labs/crit/.github/workflows/release.yml@refs/tags/v0.17.2
Rekor log index 3763503317
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:33e3a4022c60291a4978b5b22949695a6b395a456e03839987c3b1d343de1526

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool setuptools.build_meta

Background: Why install scripts are a supply-chain risk →

Dependencies 25 packages
Packages resolved 25
Stale 1
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 62 exposed · ~12,417 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
crit_run_recon ~210

Gather the model's sampling, stop tokens, chat template and config into work/recon.json

NameTypeReqDescription
comparestring–Instead: compare the run's model fingerprint with another checkpoint's (architecture, weight layout, tokenizer, template) and print what differs
drafterarray–A companion drafter to record (EAGLE-3, DFlash, DSpark or crit models drafter output); repeatable
forceboolean–Gather again over an existing work/recon.json
idstringyesExisting run identity
projectstring–crit checkout the run follows, whose settings.toml it reads (default: this checkout); a crit installed without a checkout takes any folder (default: the current one)
rootstring–Run root; defaults to PROJECT/runs
wait_secondsnumber–Seconds to wait for the command to end before returning its job to wait on with crit_job_wait (the command keeps running)

No output schema declared.

No examples provided.

crit_run_recover ~123

Explicit dead-owner lease recovery and projection rebuild; never resets attempts/deadlines

NameTypeReqDescription
idstringyesExisting run identity
projectstring–crit checkout the run follows, whose settings.toml it reads (default: this checkout); a crit installed without a checkout takes any folder (default: the current one)
rootstring–Run root; defaults to PROJECT/runs
wait_secondsnumber–Seconds to wait for the command to end before returning its job to wait on with crit_job_wait (the command keeps running)

No output schema declared.

No examples provided.

crit_run_replay ~306

Copy the run as it stood when a candidate's Eval finished, for an agent to say what it would do next with today's crit and crit-eval (records nothing)

NameTypeReqDescription
agentstring–Start an agent on every replay at once with this command (any harness; {brief}, {folder}, {root} and {number} name the replay's), wait for all, then collect
atstring–The candidate whose newest completed Eval the replays start from
beforestring–Instead: the run as it stood just before this plan was recorded (with the work done toward it since its parent's Eval, without drafts of the plan)
collectboolean–Instead: check and list the plans the replays under --out wrote
countinteger–Replays to make, one per agent (default 1)
idstringyesExisting run identity
outstringyesFolder of the replays: replay-1 ... replay-N, each a run root
projectstring–crit checkout the run follows, whose settings.toml it reads (default: this checkout); a crit installed without a checkout takes any folder (default: the current one)
rootstring–Run root; defaults to PROJECT/runs
wait_secondsnumber–Seconds to wait for the command to end before returning its job to wait on with crit_job_wait (the command keeps running)

No output schema declared.

No examples provided.

crit_run_reserve ~142

Consume an attempt before a launch

NameTypeReqDescription
candidatestring–Candidate owner; omit only for discovery
idstringyesExisting run identity
operationstringyes–
projectstring–crit checkout the run follows, whose settings.toml it reads (default: this checkout); a crit installed without a checkout takes any folder (default: the current one)
rootstring–Run root; defaults to PROJECT/runs
secondsnumber––
wait_secondsnumber–Seconds to wait for the command to end before returning its job to wait on with crit_job_wait (the command keeps running)

No output schema declared.

No examples provided.

crit_run_resolve ~143

Freeze the verified model and input identities

NameTypeReqDescription
idstringyesExisting run identity
projectstring–crit checkout the run follows, whose settings.toml it reads (default: this checkout); a crit installed without a checkout takes any folder (default: the current one)
recordobject|array|stringyesA JSON object (written to a file for the command) or a JSON file's path
rootstring–Run root; defaults to PROJECT/runs
wait_secondsnumber–Seconds to wait for the command to end before returning its job to wait on with crit_job_wait (the command keeps running)

No output schema declared.

No examples provided.

crit_run_resume ~240

Open a new segment for more candidates, optionally amending the quality terms

NameTypeReqDescription
approved_bystring–Who approved the amendment (required with --quality-budget or --exactness)
attempt_limitinteger––
candidatesinteger–Candidates this segment builds (no working time budget)
exactnessstring–Amend the speculative exactness mode
external_agent_stoppedboolean––
idstringyesExisting run identity
minutesinteger–Time-budget segment instead, or the safety window with --candidates
projectstring–crit checkout the run follows, whose settings.toml it reads (default: this checkout); a crit installed without a checkout takes any folder (default: the current one)
quality_budgetstring–Amend the drift budget: any of ppl_ratio_max, kld_mean_max, kld_p99_max
rootstring–Run root; defaults to PROJECT/runs
wait_secondsnumber–Seconds to wait for the command to end before returning its job to wait on with crit_job_wait (the command keeps running)

No output schema declared.

No examples provided.

crit_run_seal ~141

Close a candidate (sealed candidates are immutable)

NameTypeReqDescription
candidatestringyes–
failurestring–Retained failure message
idstringyesExisting run identity
lifecyclestringyes–
projectstring–crit checkout the run follows, whose settings.toml it reads (default: this checkout); a crit installed without a checkout takes any folder (default: the current one)
rootstring–Run root; defaults to PROJECT/runs
wait_secondsnumber–Seconds to wait for the command to end before returning its job to wait on with crit_job_wait (the command keeps running)

No output schema declared.

No examples provided.

crit_run_select ~119

Select a sealed eligible candidate

NameTypeReqDescription
candidatestringyes–
idstringyesExisting run identity
projectstring–crit checkout the run follows, whose settings.toml it reads (default: this checkout); a crit installed without a checkout takes any folder (default: the current one)
rootstring–Run root; defaults to PROJECT/runs
wait_secondsnumber–Seconds to wait for the command to end before returning its job to wait on with crit_job_wait (the command keeps running)

No output schema declared.

No examples provided.

crit_run_serve ~331

Serve a packaged candidate before it is sealed through crit serve, under a check attempt, until Ctrl+C: for the checks a candidate passes before sealing

NameTypeReqDescription
candidatestringyes–
checkboolean–Run the standard serving checks (consecutive requests, system message, streaming, stop string, cancelling, tool call, logprobs, template switch, stopping), keep their report and record a functional c…
datastring–With --check: crit-eval's prepared data for the run's model; the report adds the gate pre-check (honesty of short replies and one long reply, request history, device memory, the lower context), the g…
hoststring––
idstringyesExisting run identity
no_smokeboolean–With --check: leave out crit smoke, the quality component tests --check runs at the run's context and at a quarter of it (smoke/README.md)
portinteger––
projectstring–crit checkout the run follows, whose settings.toml it reads (default: this checkout); a crit installed without a checkout takes any folder (default: the current one)
rootstring–Run root; defaults to PROJECT/runs
secondsnumber–Reservation length (default: the check process cap)
wait_secondsnumber–Seconds to wait for the command to end before returning its job to wait on with crit_job_wait (the command keeps running)

No output schema declared.

No examples provided.

crit_run_settle ~159

Settle a reserved attempt: exit, logs, cleanup

NameTypeReqDescription
idstringyesExisting run identity
projectstring–crit checkout the run follows, whose settings.toml it reads (default: this checkout); a crit installed without a checkout takes any folder (default: the current one)
recordobject|array|stringyesA JSON object (written to a file for the command) or a JSON file's path
reservationstringyesReservation path relative to run
rootstring–Run root; defaults to PROJECT/runs
wait_secondsnumber–Seconds to wait for the command to end before returning its job to wait on with crit_job_wait (the command keeps running)

No output schema declared.

No examples provided.

crit_run_show ~118

Print the run, its state and its candidates as JSON

NameTypeReqDescription
idstringyesExisting run identity
projectstring–crit checkout the run follows, whose settings.toml it reads (default: this checkout); a crit installed without a checkout takes any folder (default: the current one)
rootstring–Run root; defaults to PROJECT/runs
wait_secondsnumber–Seconds to wait for the command to end before returning its job to wait on with crit_job_wait (the command keeps running)

No output schema declared.

No examples provided.

crit_run_stop ~148

Stop the run with its reason, critique, headroom and cleanup

NameTypeReqDescription
idstringyesExisting run identity
projectstring–crit checkout the run follows, whose settings.toml it reads (default: this checkout); a crit installed without a checkout takes any folder (default: the current one)
recordobject|array|stringyesA JSON object (written to a file for the command) or a JSON file's path
rootstring–Run root; defaults to PROJECT/runs
wait_secondsnumber–Seconds to wait for the command to end before returning its job to wait on with crit_job_wait (the command keeps running)

No output schema declared.

No examples provided.

crit_serve ~901

crit serve: load a sealed candidate once and answer OpenAI-compatible requests until stopped.

NameTypeReqDescription
api_keyarray–Require this bearer key; repeat for several (default: the comma-separated keys in the CRIT_API_KEY environment variable, else none)
api_key_filestring–Also accept the keys in this file, one per line; blank lines and lines starting with # are skipped
candidatestring–Candidate ID (default: the run's selected candidate)
cors_originstring–Allow browser requests from this origin, for example http://localhost:3000 or *
enginestring–Serve an engine crit pull installed, as OWNER/NAME
hoststring–Address to listen on (default: 127.0.0.1, this machine only)
idle_unloadnumber–Unload the engine's weights after this many seconds without a request; the next request loads it again (default: stay loaded)
lenientboolean–Ignore request parameters crit does not apply (unknown ones, sampling fields the package does not declare, extra samplers) instead of refusing them with 400; responses list them in X-Crit-Ignored-Par…
load_timeoutnumber–Seconds loading the candidate at startup may take (default: 600 plus the model's size at 200 MB/s, or at 50 MB/s with --verify-model)
max_concurrencyinteger–Run at most N requests at once, below the engine's declared capacity (max_concurrent_requests; default: the engine's)
max_queueinteger–Requests that may wait while the engine is busy; one more is refused at once with 429 (Anthropic 529, /api/chat 503) and Retry-After (default: 64)
model_namestring–Model ID reported to clients (default: RUN_ID/CANDIDATE_ID)
modelsstring–JSON catalog of named models from sealed runs (docs/SERVING.md)
portinteger–Port (default: 8000)
projectstring–crit repository (default: this checkout); a crit installed without a checkout takes any folder (default: the current one)
queue_timeoutnumber–Seconds a request may wait for the engine before it is refused the same way (default: no limit; --timeout starts when the engine takes the request)
reasoning_aliasboolean–Return reasoning under "reasoning" as well as "reasoning_content", for clients that read the field reasoning (off by default: a client that joins every field of a delta, as crit Eval does, would read…
recover_runtimeboolean–Recover a dead runtime owner after verifying its processes settled, then exit
resident_ram_gibnumber–Optional cap on retained model bytes in host memory
resident_vram_gibnumber–Optional cap on retained model bytes in device memory
runstring–Run ID (default: the workspace's only run)
sse_ping_intervalnumber–Send a keep-alive ping on an OpenAI or Anthropic stream after this many quiet seconds, so proxies and clients do not close it while a model loads or a prompt prefills; 0 sends none (default: 15)
ssl_certfilestring–Serve HTTPS with this PEM certificate chain
ssl_keyfilestring–The certificate's PEM private key (default: the key in --ssl-certfile)
storestring–Installed-engine store --engine reads (default: PROJECT/engines, where crit pull installs)
timeoutnumber–Seconds one request may run (default: 600)
verify_modelboolean–Read and SHA-256 every model file against the run's frozen manifest before loading (default: check file sizes only and load right away)
wait_secondsnumber–Seconds to wait for the command to end before returning its job to wait on with crit_job_wait (the command keeps running)
workspacestring–Folder containing the run-* project directories
write_launchersboolean–Write serve.cmd and serve.sh into the run folder, which start this exact command, then exit

No output schema declared.

No examples provided.

crit_serve_status ~67

A running crit serve's /health (loaded engine, readiness, capacity) and /v1/models

NameTypeReqDescription
api_keystring–One of the server's --api-key values, if it has any
urlstring–The server, without /v1

No output schema declared.

No examples provided.

Install

How do I install the crit MCP server?

crit runs locally as a PyPI package, launched with uvx crit 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 · crit

# add to Claude Code
claude mcp add crit-labs-crit -- uvx crit mcp
Common questions

What is the crit MCP server?

crit is an MCP server listed in the public MCP registry as io.github.crit-labs/crit. Build, evaluate and serve a bespoke LLM inference engine for your own GPU with crit's commands. This page covers its PyPI package (crit).

Is the crit MCP server safe to use?

crit scores 63 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. 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 crit MCP server expose?

crit exposes 62 tools: crit_run_create, crit_run_resolve, crit_run_plan, crit_run_check, crit_run_benchmark, and 57 more. Their descriptions and schemas cost roughly 12,417 tokens of context every time the server is loaded.

Is the crit MCP server still maintained?

crit 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 crit MCP server under?

crit 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 crit MCP server?

VerifyMCP ran 15 checks on crit, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about crit: Malware scan. 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.