io.github.lluvr/frame-check
PYPI · FRAME-CHECK-MCP
Deterministic structural framing analysis for AI-generated documents; no LLM call of its own.
Available components
Last scanned (1 hour ago)
Scores higher than 80% of PyPI servers
Category AI and Machine Learning
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
- 0 of 1 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to lluvr/frame-check). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 0 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability87
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 8519 tokens (~83/item across 102 items; 2 tools + 100 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
- Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Checks we ran (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- 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.
- Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
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 →
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.
- 6 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 5 Nov 26 65
First indexed and scored.
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 6 Nov 2026 · Analysed pypi/frame-check-mcp@1.2.1
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 | lluvr/frame-check |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/lluvr/frame-check/.github/workflows/publish.yml@refs/tags/v1.2.1 |
| Rekor log index | 3697937053 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:d2eb3c76f6dd0d18e51cc898ea6fd2191fc44dd3432412e9428b3c1a805e1eca |
Background: How many MCP packages publish verified provenance →
Dependencies 1 package
| Packages resolved | 1 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
frame_check ~1,168
Read a document with a structural lens: which analytical perspectives it covers, which it omits, how confidently it speaks, and which framing patterns from the Frame Vocabulary Standard fire on it. Use this when the user pastes a document and asks for a structural read, when you want to self-audit your own last response before the user acts on it, or when the user pastes another AI's reply and asks what that AI did structurally. Zero-arg invocation works for any English analytical document: `frame_check(document_text=<text>)`. The defaults produce the full output, including the divergence block (perspectives the document does not use) and a per-call suggested_next_actions block. Pass the optional parameters only when the user has provided the relevant context (source material, decision goal, working-memory budget). Compose ONE insight grounded in the cited measurements (a reading the user could not see by reading the document themselves), not a walk through the measurements one by one. The measurements are Frame Check's; the reading is yours. Cite each measurement as Frame Check's; frame the reading as a reading ('the pattern reads as X'), never as a verdict ('the document is X'). Repeated calls with identical inputs return identical measurements; zero LLM cost on the deterministic path.
| Name | Type | Req | Description |
|---|---|---|---|
| compose_budget | string | – | Default 'standard'. Switch to 'minimal' for tighter working-memory budgets (per-turn self-audit loops, batch document processing) or to 'full' when you specifically need the inline claim_level_treatm… |
| divergence_rendering | string | – | Default 'list'. Switch to 'teaching_questions' when the absent-frame records should carry a teaching_question field for surfacing as questions rather than identifiers. All other modes return the same… |
| document_text | string | yes | The document to analyse. English. 300 to 10,000 words is the validated range; under 100 words the analysis carries a low-confidence note, over 1,000,000 characters returns a truncation guidance. Mark… |
| include_divergence | boolean | – | Default true. You do not need to pass this. The divergence block (frame patterns the document does not use, sorted by signal_strength) is the headline output and ships by default. Set explicitly to f… |
| include_frame_opportunities | boolean | – | Default false. Set true when the user wants up to 3 LLM-augmented document-specific questions composed from absent-frame teaching questions plus the document's content. Adds frame_opportunities to th… |
| source_text | string | – | Pass when the user has the source material the document was supposed to ground in (research report, SEC filing, primary source). Unlocks digit-level source-fidelity verification (Layer 4) plus a sent… |
| user_context | string | – | Pass when the user has stated their situation, role, or decision context in the conversation (for example, 'I am a startup founder making a hire decision in healthcare AI', 'reviewing a research pape… |
| user_goal | string | – | Pass when the user has stated a goal for invoking Frame Check. One of: 'decide' (working through a choice), 'brainstorm' (exploring options), 'persuade' (writing to influence), 'learn' (understanding… |
No output schema declared.
No examples provided.
frame_compare ~332
Compare the framing of two documents on the same subject. Surfaces shared blind spots, unique coverage gaps, voice / temporal / epistemic deltas, and a structured framing-differences narrative with per-dimension reader implications. Use this when the user has two documents on the same subject (two AI responses to the same prompt, two analyst memos, an earnings release versus a press summary) and wants to see how they frame the same question differently. Pass `document_a_label` and `document_b_label` only when the user has named the documents (for example 'Gemini response' and 'Claude response'). Otherwise the comparison narrative falls back to 'Document A' and 'Document B'. Cite each measurement as Frame Check's; never imply that one document is better, more rigorous, or more biased than the other. The structural comparison surfaces what differs; the reader judges what the difference means. Repeated calls with identical inputs return identical results. No LLM is invoked.
| Name | Type | Req | Description |
|---|---|---|---|
| document_a_label | string | – | Optional short label for document A (e.g. 'Industry view' or 'Gemini response'). Used in the comparison narrative. Defaults to 'Document A'. |
| document_a_text | string | yes | The first document to compare. English. 300-10,000 words. |
| document_b_label | string | – | Optional short label for document B. Defaults to 'Document B'. |
| document_b_text | string | yes | The second document to compare. English. 300-10,000 words. Should be on the same subject as document_a_text for the comparison to be meaningful. |
No output schema declared.
No examples provided.
How do I install the io.github.lluvr/frame-check MCP server?
io.github.lluvr/frame-check runs locally as a PyPI package, launched with uvx frame-check-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 · frame-check-mcp
claude mcp add lluvr-frame-check -- uvx frame-check-mcp
What is the io.github.lluvr/frame-check MCP server?
io.github.lluvr/frame-check is an MCP server listed in the public MCP registry as io.github.lluvr/frame-check. Deterministic structural framing analysis for AI-generated documents; no LLM call of its own. This page covers its PyPI package (frame-check-mcp).
Is the io.github.lluvr/frame-check MCP server safe to use?
io.github.lluvr/frame-check scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 6 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.lluvr/frame-check MCP server expose?
io.github.lluvr/frame-check exposes 2 tools: frame_check, frame_compare. Their descriptions and schemas cost roughly 1,500 tokens of context every time the server is loaded.
Is the io.github.lluvr/frame-check MCP server still maintained?
io.github.lluvr/frame-check is still listed as active in the MCP registry. We last reached this channel on 6 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.lluvr/frame-check MCP server under?
io.github.lluvr/frame-check 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.lluvr/frame-check MCP server?
VerifyMCP ran 15 checks on io.github.lluvr/frame-check, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about io.github.lluvr/frame-check: Stability. One category scores 0 for that reason, because we only credit what we can confirm. 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.