MCP server for generating academic diagrams, statistical plots, figure packages, and visual evaluations from research context through PaperBanana's multi-agent illustration pipeline.
Open the source and read safety notes before installing.
Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.
Decision playbook
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
0
63
—
No baseline selected
No major trust-signal divergence detected in the current selection.
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Source provenance statusRequired
Marked as source-backed.
Metadata reviewed
No reviewed flag detected in metadata.
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Trust level risk gateRequired
Trust level does not block evaluation.
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Package verification flag
No package verification flag provided.
Checksum metadata
No checksum provided for downloaded artifact.
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
Baseline comparison available
No baseline peer selected yet.
Diverging trust signals identified
No major trust-signal divergence found.
Setup at a glance
Copy-ready — paste the snippet to get started.
Adoption plan
Current risk score 24/100. Use staged verification before broader rollout.
Validate source and review signals before any execution.
Confirm source provenanceRequired
Source URL/provenance metadata is present.
Confirm metadata review state
No review metadata found; increase manual validation.
Verify install payload
Install/config payload exists and can be inspected.
Confirm safety, privacy, and package integrity signals.
Review safety notesRequired
Safety notes are present.
Review privacy notesRequired
Privacy notes are present.
Verify package integrity metadata
No package verification/checksum metadata.
Adopt in controlled steps based on the selected plan.
Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Evidence readiness
Missing required evidence: Metadata review. Risk score 31.
Source repository/provenance is listed.
Required in this preset
Review metadata is missing.
Required in this preset
Safety notes are present.
Required in this preset
Privacy notes are present.
Optional in this preset
Package integrity metadata is missing.
Optional in this preset
Install payload is available.
Required in this preset
Required gaps: Metadata review
Decision timeline
Blocking gaps: Check metadata review status. Risk 28.
triage
Source/provenance metadata is available.
triage
Review metadata is missing.
verify
Safety notes are available.
verify
Privacy notes are available.
verify
Package integrity metadata is missing.
rollout
Install payload is available.
Blockers: Check metadata review status
Prerequisite readiness
5 prerequisites to line up before setup. Have accounts and credentials ready first. Includes a review or approval gate.
Safety & privacy surface
6 safety and 5 privacy notes across 5 risk areas. Review closely: network access, third-party handling.
Disclosure: MIT-licensed open source implementation inspired by the PaperBanana research paper. The project describes itself as unofficial and not affiliated with or endorsed by the original paper authors or Google Research.
{
"mcpServers": {
"paperbanana": {
"command": "uvx",
"args": ["--from", "paperbanana[mcp]", "paperbanana-mcp"],
"env": {
"OPENAI_API_KEY": "REPLACE_WITH_OPENAI_API_KEY"
}
}
}
}PaperBanana MCP exposes an academic figure generation workflow through MCP. It lets Claude and other MCP clients generate methodology diagrams, statistical plots, visual critiques, batch outputs, and full-paper figure packages from research context, captions, datasets, manifests, and reference images.
Use it when a research workflow needs fast visual drafts inside the same coding or writing environment that holds the paper context. It is best treated as a figure drafting and review assistant: generate, inspect, iterate, and verify before any publication or external use.
These sources were reviewed on 2026-06-06. Prefer the live repository, MCP README, PyPI metadata, license, MCP implementation, registry metadata, package metadata, and environment template for current setup and provider details.
Run the MCP server directly with uvx:
uvx --from "paperbanana[mcp]" paperbanana-mcp
Add the server to your MCP client config:
{
"mcpServers": {
"paperbanana": {
"command": "uvx",
"args": ["--from", "paperbanana[mcp]", "paperbanana-mcp"],
"env": {
"OPENAI_API_KEY": "REPLACE_WITH_OPENAI_API_KEY"
}
}
}
}
For local development, install the MCP extra from a clone and use the generated console script:
pip install -e ".[mcp]"
paperbanana-mcp
PaperBanana is most useful with detailed research context, which also makes it sensitive. Treat prompts, papers, datasets, generated figures, reference images, and output folders as research data. Review provider terms before sending unpublished work, confidential datasets, or embargoed manuscripts.
Use dry_run for orchestration planning, start with small manifests, and review
all outputs manually. Generated scientific figures can look polished while still
misrepresenting methods, axes, statistics, causal relationships, or uncertainty.
Show that PaperBanana MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/paperbanana-mcp-server)PaperBanana MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | MCP server for generating academic diagrams, statistical plots, figure packages, and visual evaluations from research context through PaperBanana's multi-agent illustration pipeline. Open dossier | MCP server for controlling Draw.io and diagrams.net diagrams from Claude, including document discovery, page management, layers, shapes, edges, Mermaid import, diagram import/export, and a built-in editor mode. Open dossier | Local-first codebase intelligence MCP server that indexes repositories with tree-sitter, stores searchable chunks in DuckDB, and gives Claude semantic search, regex search, daemon status, and deep code research tools. Open dossier | Official ElevenLabs MCP server for generating speech, designing voices, cloning voices, transcribing audio, creating sound effects, and working with conversational audio agents through the ElevenLabs API. Open dossier |
|---|---|---|---|---|
| Next steps | ||||
| Trust | ||||
| Review status | Not reviewed | Not reviewed | Not reviewed | Not reviewed |
| Package trust | Package not verified | Package not verified | Package not verified | Package not verified |
| Source provenance | Source-backed | Source-backed | Source-backed | Source-backed |
| Submitter | oktofeesh1 | oktofeesh1 | oktofeesh1 | oktofeesh1 |
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Brand | — | |||
| Category | mcp | mcp | mcp | mcp |
| Source | Source-backed | Source-backed | Source-backed | Source-backed |
| Author | PaperBanana Contributors | Lukas Gazo | ChunkHound | ElevenLabs |
| Added | 2026-06-06 | 2026-06-06 | 2026-06-06 | 2026-06-06 |
| Platforms | ||||
| Harness | ||||
| Source repo | — | — | — | — |
| Safety notes | ✓PaperBanana can send research context, paper excerpts, captions, datasets, prompts, generated images, and evaluation inputs to configured model providers. Generation, evaluation, batch, and orchestration tools may make many provider API calls and incur cost, especially with auto-refine or large manifests. The orchestration tool supports `dry_run` for planning only; use it before generating a full-paper figure package. The server writes output directories, final images, metadata, reports, LaTeX snippets, captions, and compressed `.mcp.jpg` files for oversized tool-result images. Generated academic diagrams and plots can be inaccurate, misleading, or overfit to prompt wording; review every figure before publication or citation. Avoid enabling `SKIP_SSL_VERIFICATION` unless you have an explicit proxy requirement and understand the transport risk. | ✓Draw.io MCP Server can create, edit, delete, import, export, rename, copy, and reorganize diagram pages, layers, shapes, edges, labels, metadata, and Mermaid-derived content. Live operations target connected Draw.io browser tabs or the built-in editor; verify the selected document and page before allowing destructive edits. The server can run local HTTP and WebSocket endpoints, optionally with TLS or auto-generated self-signed certificates; avoid binding it to untrusted network interfaces. Browser-extension mode links a browser tab to the MCP server, so only connect tabs containing diagrams that the agent is allowed to inspect or modify. Export tools can write or return XML, SVG, and PNG files with embedded diagram data; review outputs before sharing them externally. Use trusted package sources, pin versions for repeatable workflows, and review generated diagrams before committing architectural or security documentation. | ✓ChunkHound reads source files, Markdown, text, PDFs, and supported config files under the target directory and stores indexed chunks in a local database. Realtime indexing and daemon mode can continue watching project files after the initial MCP connection. Code research and web search tools require embedding, reranking, and LLM configuration and may invoke local CLIs or external model APIs depending on settings. Exclude generated files, vendored dependencies, secrets, large artifacts, and unrelated repositories before indexing broad workspace roots. Review MCP client configuration carefully when using an absolute project path in a global Claude Desktop config. | ✓ElevenLabs MCP Server can call paid ElevenLabs API endpoints; text-to-speech, voice design, voice cloning, audio isolation, transcription, sound generation, music, and agent workflows can consume account credits. Voice cloning and voice conversion can create realistic synthetic speech, so require documented consent and review before processing a person's voice or publishing generated audio. Generated speech, sound effects, music, transcripts, and conversation-agent configuration can affect public-facing content; review prompts, voice IDs, output format, language, and destination before publishing or sending. File output mode writes generated files to disk under the configured base path; restrict that path to an approved directory and avoid broad home, desktop, or shared folders in production. Use separate API keys or workspaces for test and production clients, monitor credit usage, and disable tools in clients that should not spend credits. Some operations may take longer than normal MCP tool timeouts; do not retry expensive generation calls blindly. |
| Privacy notes | ✓Provider requests may include unpublished research text, PDFs, statistical data, captions, reference images, prompts, and visual critique feedback. Local `.env` files can contain OpenAI, Azure OpenAI, Google Gemini, OpenRouter, Ollama, or compatible provider configuration. Output folders may contain intermediate images, final figures, run inputs, metadata, batch reports, orchestration plans, captions, and paths to source files. Logs and progress events can include tool names, run identifiers, validation errors, file paths, manifest names, and generation status. Check model-provider retention, training, and data-processing terms before sending confidential manuscripts or sensitive datasets. | ✓Diagrams can include private architecture, network topology, cloud account names, customer systems, credentials embedded in labels, incident details, internal process maps, or product plans. The MCP client can receive diagram XML, SVG, PNG exports, page names, layer names, selected-cell data, shape metadata, browser tab document metadata, and imported Mermaid content. Local editor and browser-extension workflows may leave diagrams, exported files, browser state, TLS material, and logs on disk. Treat exported SVG or PNG files with embedded XML as source files, because they can contain full editable diagram data beyond the visible image. Clear temporary files, generated certificates, and MCP logs when they are no longer needed for the diagram workflow. | ✓Indexed chunks, file paths, symbols, comments, Markdown, PDFs, configuration values, database files, daemon state, and search results can reveal proprietary source code and internal architecture. Embedding, reranking, LLM, and web search providers may receive code-derived queries or snippets if configured. Local ChunkHound database files, logs, daemon state, and MCP transcripts may retain code-derived context after the session ends. Avoid sharing ChunkHound databases, config files with API keys, verbose logs, research outputs, and screenshots from private repositories. | ✓The MCP client can expose ElevenLabs API keys, voice IDs, text prompts, voice descriptions, uploaded audio samples, generated audio paths, transcripts, diarized speaker labels, and conversational-agent settings. Uploaded audio and generated outputs may contain biometric voice characteristics, names, background sounds, private conversations, or copyrighted material. File, resource, and both output modes can retain generated audio locally, in MCP resources, in logs, or in chat transcripts depending on the client. Treat voice samples and transcripts as sensitive data, and delete generated files or cached resources when they are no longer needed. Review ElevenLabs account, retention, residency, and enterprise data-residency settings before using the server with regulated or customer data. |
| Prerequisites |
|
|
|
|
| Install | | | | |
| Config | | | | |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Let Claude create, inspect, edit, import, and export Draw.io diagrams through a local MCP server with built-in editor and browser-extension options.
Run `chunkhound mcp` to give Claude local semantic and regex code search with optional LLM-backed research over indexed repositories.
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.