Skip to main content
Glama
deenesjakoruzh
lluvr

frame-check-mcp

by lluvr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Frame Check

Sehen Sie, was Ihnen ein Dokument vorenthält.

Frame Check ist ein Werkzeug zur strukturellen Framing-Analyse. Es benennt, welche Perspektiven ein Dokument einnimmt, welche es auslässt und wie es den Leser positioniert. Numerische Behauptungen werden, sofern Abdeckung vorhanden ist, mit maßgeblichen Quellen abgeglichen.

Quickstart (MCP-Server)

Das PyPI-Paket frame-check-mcp ist der Model Context Protocol-Server. Er läuft lokal und stellt jedem MCP-kompatiblen KI-Client (Claude Desktop, Cursor, Cline, Continue.dev usw.) eine deterministische strukturelle Framing-Analyse als Werkzeug zur Verfügung.

pip install frame-check-mcp

Verweisen Sie dann Ihren MCP-Client auf den installierten Einstiegspunkt. Fügen Sie für Claude Desktop Folgendes zu claude_desktop_config.json hinzu:

{
  "mcpServers": {
    "frame-check": {
      "command": "frame-check-mcp"
    }
  }
}

Starten Sie den Client neu. Dann in jedem Gespräch: "Can you frame-check this document?" Vollständige Installations- und Verifizierungsdetails finden Sie in MCP_SERVER.md.

Related MCP server: Kluster.ai Verify MCP

Was es tut

Übergeben Sie ein Dokument und Frame Check liefert:

  • Ein strukturelles Framing-Profil: Welche der fünf analytischen Perspektiven (Ursachen, Risiken, Stakeholder, Trends, Unsicherheit) das Dokument abdeckt, welche es auslässt und die Dichte der jeweiligen Perspektive.

  • Sprachliche und epistemische Haltung: Wie das Dokument den Leser positioniert und welcher Anteil der Behauptungen Quellen zugeschrieben wird.

  • Zeitliche Ausrichtung: Ob das Dokument seine Schlussfolgerungen auf historische Daten, den aktuellen Stand oder Prognosen stützt.

  • Übereinstimmungen mit dem Frame Vocabulary Standard: Benannte Frame-Muster, deren regelbasierte Signale auf den Text reagieren, jeweils mit Identifikationshinweisen und ausgearbeiteten Beispielen. Übereinstimmungen sind auf Kandidatenebene; die Präzision gegenüber einer Kennzeichnung durch mehrere Quellen ist ein aktives Forschungsgebiet.

  • Verifizierung des Quellennetzwerks: Numerische Behauptungen werden anhand von SEC EDGAR, FRED, Weltbank, REST Countries, Alpha Vantage und Wolfram Alpha überprüft, sofern diese Anbieter eine Abdeckung bieten.

  • Eine optionale KI-Erzählung, die das Framing auf Prosaebene interpretiert. Deutlich gekennzeichnet, damit Leser die Interpretation des Sprachmodells nicht mit deterministischer Messung verwechseln.

Ansatz

Strukturelle Messung ist die Basis. Jede Framing-Behauptung, die das Werkzeug aufstellt, wird aus deterministischen Musterabgleichen berechnet und liefert für denselben Input immer das gleiche Ergebnis. KI-gestützte Interpretation ist als Anreicherung verfügbar, wenn ein API-Schlüssel konfiguriert ist, wird jedoch als solche gekennzeichnet und niemals hinter der strukturellen Ebene verborgen.

Die Verifizierung ist begrenzt. Das Werkzeug verifiziert numerische Behauptungen nur anhand von Anbietern mit echter Abdeckung für den jeweiligen Behauptungstyp und zeigt seine eigenen Kalibrierungsergebnisse (Präzision, Recall, F1 pro Anbieter) an, anstatt Urteile ohne Beweise zu fällen.

Die Erkennung benannter Muster ist eine separate Zuverlässigkeitsebene neben dem strukturellen Profil. Detektor F1 = 0,36 gegenüber Experten-Labelern in einer vorregistrierten Validierung, unterhalb der nützlichen Schwelle von 0,4. Der Wechsel zur Darstellung von Konstrukt-Ehrlichkeit (Markierungen für Untererfassung, Dichte-Vorbehalte, Vertrauenszustände) anstelle von selbstbewussten Labels ist der tragende Anspruch bei v0; eine Studie zur Lesehilfe (Track B, vorregistriert) testet, ob diese Darstellung einem Leser tatsächlich hilft, Framing zu erkennen, das er sonst übersehen würde.

Ehrliche Grenzen und erwartete gegnerische Lesarten sind in ANTICIPATED_CRITIQUES.md katalogisiert.

Dokumentation

  • METHODOLOGY.md — vollständiges Methodik-Papier (v0.2 Entwurf)

  • MCP_SERVER.md — MCP-Server-Referenz (Werkzeuge, Ressourcen, Prompts)

  • MCP_CLIENT_CONFORMANCE_v1.md — 32/32 Konformitäts-Roundtrips gegen das installierte Wheel

  • FRAME_DIVERGENCE_v1.md und FRAME_DIVERGENCE_v2.md — Divergenz-Architektur

  • data/frame_library/ — FVS-Katalog mit 20 Einträgen und ausgearbeiteten Beispielen

  • ANTICIPATED_CRITIQUES.md — selbst aufgeführte gegnerische Lesarten

  • VALIDATION_PROGRAM.md — Beobachtungs- + formale Validierungspläne

Tests ausführen

pip install -r requirements.txt
python3 run_tests.py

49 Testsuiten, ca. 3 Minuten. Beinhaltet 63 gegnerische Dispatcher-Tests in test_mcp_adversarial.py sowie die Abdeckung der V4.2-Engine + Klassifikator.

Lizenz

Apache-2.0 für Code; CC-BY-4.0 für die FVS-Bibliothek und ausgearbeitete Beispiele (siehe NOTICE für die Aufzählung pro Verzeichnis).

Zitierung

Wenn Frame Check in Ihrer Arbeit nützlich ist, siehe CITATION.cff für die zitierfähige Form. Frame Check wurde von Lovro Lucic verfasst; die namentliche Autorenschaft ist das primäre Glaubwürdigkeitskapital des Projekts gemäß der Disziplin der Konstrukt-Ehrlichkeit.

Mitwirken

Sign-off-by-DCO erforderlich gemäß CONTRIBUTING.md. Governance gemäß GOVERNANCE.md (BDFL-Modell mit benannten Erzwingungsfunktionen für Entscheidungen zur Kanon-Förderung). Einbindung externer Gutachter gemäß REVIEWERS.md.

Probleme

https://github.com/lluvr/frame-check-mcp/issues

Available Tools

2 tools
frame_checkA

Deterministic structural framing analysis. Returns analysis (measurements) + agent_guidance (composition discipline, scope-regime guidance, faithfulness rules) + provenance (versions, license, citation). When source_text is provided, also runs Layer 4 source_fidelity and Layer 11 grounding_decomposition with a Monte-Carlo-verified scope regime. When include_divergence=true (default at 0.8.0), the response carries a top-level divergence block sorted by signal_strength. The agent's role is to compose ONE insight grounded in the cited measurements (a reading the user could not see by reading their own document), not to walk the measurements one by one. The measurements are Frame Check's; the reading is the agent's. Cite measurements 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; the agent's insight is a composition over them.

ParametersJSON Schema
NameRequiredDescriptionDefault
document_textYesThe document to analyse. English. 300-10,000 words. Markdown accepted. This is the text whose framing you want named.
source_textNoOptional. The source material the document is supposed to ground in (research report, filing, primary source). Unlocks Layer 4 source_fidelity (digit-level match) and Layer 11 grounding_decomposition (sentence-level G/F/P) with a scope regime telling you which layer to trust on number-dense sources. Without this, only structural framing analysis runs.
prefer_contract_versionNoOptional. Coverage contract version the client prefers. 1 (default): emit both v1 coverage and v2 coverage_v2 (Phase 1 compatibility window). 2: emit only coverage_v2 and omit v1 (for clients that have migrated and want to avoid payload duplication). See MCP_CONTRACT_V2_PROPOSAL.md and MCP_SERVER.md 'Contract versions' section. When Phase 3 activates, v1 will stop emitting regardless of this parameter.
include_divergenceNoOptional. Frame divergence output per FRAME_DIVERGENCE_CONTRACT_v1 Part 2. When true (default at 0.8.0; was opt-in at 0.7.x), the response carries a top-level `divergence` block (absent_frames array sorted by signal_strength tier, FaithfulnessEnvelope with divergence_summary prose) and two `agent_guidance` additions (how_to_render_divergence, absence_is_not_prescription). MCP surface does not invoke any LLM for divergence; the caller's agent model completes the composition using the guidance + library resources. Set explicitly to false to receive the v0.7.x-shape response with no divergence block. Default: true.
domain_hintNoOptional. Hint about the document's domain used to filter absent frames for domain relevance. Only meaningful when include_divergence=true. If omitted, the envelope reports domain_inferred='unfiltered' and all absent frames are returned. Domain-metadata-based filtering is a future contract minor version; the current implementation echoes the hint to the envelope without field-level filtering (documented in envelope.limitations).
divergence_renderingNoOptional. How the caller wants absent-frame records decorated. Only affects AbsentFrameRecord decoration (teaching_question field present in 'teaching_questions' mode); all other modes return the same data. The caller's agent model renders per this preference with faithfulness guarantees from agent_guidance.how_to_render_divergence. Default: 'list'.
catalog_version_pinNoOptional. Pin the FVS catalog version used for absent-frame set difference. If omitted, the latest stable catalog version is used (currently library_v3 per commit 9abeb3d). Unsupported pins are coerced to library_v3 with a limitation note in envelope.limitations.
user_contextNoOptional. The user's situation, role, or decision context in plain prose (e.g., 'I'm a startup founder making a hire decision in healthcare AI', 'reviewing a research paper on language model alignment', 'drafting a Substack post on agent safety'). When provided, agent_guidance.how_to_render_divergence is extended to instruct the caller's model to filter divergence relevance for this context. The MCP does NOT echo the value back into the response (privacy posture); the caller's agent has it from the call args. Discipline: the context personalizes RELEVANCE FILTERING; never PRESCRIPTION. The absence_is_not_prescription guarantee extends to contextual surfacing. Default: omitted (no contextual filtering). Maximum length 2000 chars.
include_frame_opportunitiesNoOptional. Opt-in flag for LLM-augmented frame-opportunity composition (Item 12 of the substrate-side composition roadmap). When true, divergence.frame_opportunities carries up to 3 document-specific questions composed by the LLM from absent-frame teaching questions plus the document's content. Each opportunity carries model_provenance with model name, cost_usd, and is_deterministic=false. The deterministic substrate (clusters, patterns, absences) is unchanged. Cost is bounded at ~0.001 USD per invocation (3 Gemini Flash calls max). Falls back to empty opportunities list with available=false if GEMINI_API_KEY is not set or the google.genai library is unavailable. Default: false (deterministic substrate only).
user_goalNoOptional. The user's stated goal for invoking Frame Check. One of 'decide', 'brainstorm', 'persuade', 'learn', 'audit'. When provided, absent_frames carry a goal_relevance dict for frames load-bearing for the chosen goal, and the absent_frames sort promotes goal-relevant entries within their signal_strength tier (goal precedes genre in the within-tier ranking). 'audit' is the default-equivalent posture: no goal-specific override is applied; the existing catalog/coverage/genre ranking stands. When omitted, behavior matches 'audit'. Substrate-side composition Item 11.
compose_budgetNoOptional. Bound the substrate's output volume so an agent in a tight working-memory budget can request a compact reading without losing structural shape. 'minimal' = top-3 absent_frames, top-1 absence_cluster, top-1 frame_pattern. 'standard' = top-5 absent_frames, all clusters, all patterns. 'full' (default) = unfiltered. The envelope.tier_counts always reflects PRE-slice counts so the agent sees the truncation honestly; divergence.compose_budget_applied carries per-layer returned/total counts. Substrate-side composition L5 interface UX. Backwards-compatible: omit to preserve current behavior.

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden and excels: it declares determinism, output structure, agent's role, and limitations (e.g., 'The measurements are Frame Check's; the reading is the agent's'). No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose but becomes verbose with detailed instructions and repeated guidance. While well-structured, it could be trimmed by ~30% without losing meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (11 params, no output schema), the description covers response components and behavioral nuances well. Missing explicit field-level structure of divergence block, but agent_guidance hints at rendering instructions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds value by explaining defaults, version behavior, and interaction between parameters (e.g., domain_hint only meaningful when include_divergence=true). This exceeds the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Deterministic structural framing analysis' and lists output components (measurements, agent_guidance, provenance). It explicitly distinguishes from sibling 'frame_compare' by focusing on single-document analysis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides guidance on when to use source_text (for layers 4 & 11), when include_divergence is default, and agent role. However, it does not explicitly exclude use cases or contrast with frame_compare, so it lacks explicit when-not advice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

frame_compareA

Deterministic structural comparison of two documents on the same subject. Returns analysis (per-document summaries plus the cross-document comparison: shared blind spots, unique coverage gaps, voice / temporal / epistemic deltas, and a structured framing-differences narrative with per-dimension reader implications) + agent_guidance (what comparison tells and does not tell you, how to cite without implying a ranking) + provenance. Repeated calls with identical inputs return identical results. No LLM is invoked.

ParametersJSON Schema
NameRequiredDescriptionDefault
document_a_textYesThe first document to compare. English. 300-10,000 words.
document_b_textYesThe 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.
document_a_labelNoOptional short label for document A (e.g. 'Industry view' or 'Gemini response'). Used in the comparison narrative. Defaults to 'Document A'.
document_b_labelNoOptional short label for document B. Defaults to 'Document B'.

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses that the tool is deterministic, returns identical results for identical inputs, and does not invoke an LLM. It also explains what the output includes (analysis, agent_guidance, provenance), providing transparency beyond basic behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured, starting with the core purpose, then listing outputs, and finally additional traits (deterministic, no LLM). It is slightly long but each sentence adds value, and it front-loads the most important information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description thoroughly explains what the tool returns (analysis, agent_guidance, provenance). It covers parameter constraints (word count, language, same subject) and behavioral traits. The context is complete for an agent to understand when and how to use the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds meaningful context: documents must be English, 300-10000 words, and on the same subject. It also clarifies that labels are optional and used in the narrative, which goes beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool does 'deterministic structural comparison of two documents on the same subject' and lists specific outputs (per-document summaries, cross-document comparison, etc.). It uses a specific verb ('compare') and resource ('two documents'), distinguishing it from the sibling tool 'frame_check'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use (documents on same subject, deterministic comparison) but does not explicitly state when not to use or compare with alternatives. It notes that repeated calls return identical results and that no LLM is invoked, but lacks direct guidance on choosing this over the sibling tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv0.1.0
    • First observedframe_check
    • First observedframe_compare
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.3/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: one analyzes a single document, the other compares two documents. There is no ambiguity.

Naming Consistency5/5

Both tools follow the consistent 'frame_<verb>' pattern (frame_check, frame_compare). The naming is predictable and uniform.

Tool Count3/5

With only two tools, the server feels minimal. While the tools are well-scoped, a server for structural analysis might benefit from additional tools for tasks like batch comparison or result export.

Completeness4/5

The server covers the two core operations (single analysis and pairwise comparison). Minor gaps exist, such as lacking a tool for multi-document analysis or aggregation, but the main use cases are addressed.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • BigContext MCP

    Rixmerz
    A
    license
    B
    quality
    D
    maintenance
    Enables working with large documents of any size by intelligently segmenting them and using TF-IDF search to retrieve only relevant fragments, preventing context window saturation. Provides 31 domain-agnostic tools for document ingestion, semantic analysis, epistemological validation, and extraction verification across formats like PDF, EPUB, and HTML.
    31
    MIT

  • clearon-source-audit

    kwgoodwin
    A
    license
    B
    quality
    C
    maintenance
    Enables revision-bound source audits with exact article fingerprinting, claim-to-source mapping, quotation verification, and immutable JSON evidence reports for prepublication review.
    9
    MIT