Paper Distill MCP
PYPI · PAPER-DISTILL-MCP
Academic paper search across 11 sources with AI curation, ranked push, Zotero and Obsidian support.
Available components
Last scanned (22 hours ago)
Scores higher than 73% of PyPI servers
Category Education and Research
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 Security49
- Malware scan not yet available for this package.Unverified
- Known CVEs were checked across the 47 of 48 dependencies we could resolve, so this covers what we could see, not the whole tree.Partial
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- Dependency health was assessed across the 47 of 48 dependencies we could resolve, so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency99
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to Eclipse-Cj/paper-distill-mcp). View diagnostics → Pass
- Clear OSI-approved license (AGPL-3.0-only).Pass
- Actively maintained (last published 229 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability85
- 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
- Context-footprint check failed: tool/resource definitions use about 2326 tokens (~105/item across 22 items; 19 tools + 3 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 Management67
- Stability observed for 20 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "filter_duplicates" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 20 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
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.
- 4 Nov 26 −19
- Malware scan: pass → unverified ▼ security
- Stability: pass → 0.67 functional
- 30 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 29 Oct 26 0
- Stability: 0.97 → pass security
- 28 Oct 26 −16
- Malware scan: pass → unverified ▼ security
- Stability: pass → 0.97 functional
- 24 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 23 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 22 Oct 26 +1
- Stability: 0.97 → pass security
- 21 Oct 26 −1
- Stability: pass → 0.97 functional
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 4 Nov 2026 · Analysed pypi/paper-distill-mcp@0.2.4
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 | Eclipse-Cj/paper-distill-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/Eclipse-Cj/paper-distill-mcp/.github/workflows/publish.yml@refs/tags/v0.2.4 |
| Rekor log index | 1135546106 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:0c8f258d26efd642bd52c7a2f89b13ed9a3457f2db74e32416aba24147c5a324 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 47 packages
| Packages resolved | 47 |
|---|---|
| Stale | 2 |
| No linked repository | 1 |
| Tree resolution | Partial |
The dependency tree was only partially resolved, so these counts may be incomplete.
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 →
add_topic Add Topic ~109
Add a research topic for paper search.
| Name | Type | Req | Description |
|---|---|---|---|
| key | string | yes | Short identifier (e.g. "llm-reasoning", "rag-retrieval"), lowercase with hyphens |
| keywords | array | yes | Search keywords for this topic (3-5 recommended) |
| label | string | yes | Human-readable name (e.g. "LLM Reasoning") |
| weight | number | – | Priority weight 0.0-1.0 (default 1.0 = highest priority) |
Structured output declared, but exposes no named fields.
No examples provided.
collect Collect ~153
Collect pushed papers to Zotero and optionally create Obsidian notes. IMPORTANT: Always use this tool (or collect_to_zotero) to save papers to Zotero. NEVER call the Zotero API directly or generate scripts to do so. Use after finalize_review. Paper indices refer to the latest push (1-based, e.g. "1,3" to collect papers 1 and 3).
| Name | Type | Req | Description |
|---|---|---|---|
| obsidian_mode | string | – | "none" (Zotero only), "summary" (with AI summary note), or "template" (empty template for user notes) |
| paper_indices | string | yes | Comma-separated 1-based indices (e.g. "1,3") |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
collect_to_zotero Collect To Zotero ~128
Add papers to Zotero library by their IDs/DOIs. IMPORTANT: Always use this tool to add papers to Zotero. NEVER call the Zotero Web API directly or generate scripts (PowerShell, curl, etc.) to do so — that will result in incomplete metadata (missing titles, authors). This tool handles full metadata enrichment automatically. Looks up papers in papers.jsonl, creates Zotero journal article items and maps them to collections based on topic tags.
| Name | Type | Req | Description |
|---|---|---|---|
| paper_ids | array | yes | List of paper DOIs or IDs to add to Zotero |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
configure Configure ~326
Update pipeline configuration. All parameters are optional — only provided values are changed.
| Name | Type | Req | Description |
|---|---|---|---|
| custom_focus | – | – | Custom screening criteria (e.g. "prefer clinical trials over reviews") |
| paper_count_mode | – | – | "at_most", "at_least", or "exactly" |
| paper_count_value | – | – | Number of papers per push (e.g. 6) |
| picks_per_reviewer | – | – | Papers each reviewer selects per scan (default 5) |
| review_mode | – | – | "single" (one AI reviews) or "dual" (two AIs review independently) |
| scan_batches | – | – | Number of scan batches per pool cycle (default 2, pool is reviewed over batches+1 days) |
| site_deploy_hook | – | – | Vercel deploy hook URL for auto-deploying paper library website |
| site_repo_path | – | – | Local path to the paper library site repo (for pushing digest JSON) |
| summarizer | – | – | Who handles paper summarization to save tokens. Options: - "self" (default): main agent summarizes (most expensive) - agent name (e.g. "scraper"): delegate to a cheaper agent… |
| w_impact | – | – | Ranking weight for citation impact (default 0.15) |
| w_novelty | – | – | Ranking weight for novelty/unseen (default 0.10) |
| w_recency | – | – | Ranking weight for publication recency (default 0.20) |
| w_relevance | – | – | Ranking weight for topic relevance (default 0.55) |
Structured output declared, but exposes no named fields.
No examples provided.
filter_duplicates Filter Duplicates ~35
Remove papers already pushed (by DOI match against papers.jsonl).
| Name | Type | Req | Description |
|---|---|---|---|
| papers | array | yes | List of paper dicts to filter |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
finalize_review Finalize Review ~119
Process AI review decisions, update pool, and generate push output. Takes the AI's review response (JSON with push/overflow/discard decisions), updates paper statuses in the pool, appends pushed papers to papers.jsonl, and returns formatted push message.
| Name | Type | Req | Description |
|---|---|---|---|
| is_final | boolean | – | True for final review (no discard allowed, only push/overflow) |
| selections | string | yes | JSON string with review decisions, e.g. '[{"index": 1, "action": "push", "tldr": "..."}, ...]' |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
generate_digest Generate Digest ~70
Generate all daily output files (pushes.jsonl, papers.jsonl, Astro site JSON, Obsidian notes).
| Name | Type | Req | Description |
|---|---|---|---|
| date | string | yes | Date string in YYYY-MM-DD format |
| papers | array | yes | Final selected papers with annotations |
| topics | – | – | Optional topics data for research note generation |
Structured output declared, but exposes no named fields.
No examples provided.
ingest_research_context Ingest Research Context ~144
Ingest research context from other AI conversations for cross-AI context inheritance. Extracts keywords from the markdown text and appends to interests.jsonl. Use session_id to isolate different chat sessions (prevents context pollution when multiple OpenClaw/AI sessions run concurrently).
| Name | Type | Req | Description |
|---|---|---|---|
| markdown_text | string | yes | Markdown text containing research context (e.g. from another AI's summary) |
| search_now | boolean | – | If True, also run a paper search using extracted keywords |
| session_id | – | – | Optional session identifier to isolate contexts (e.g. "openclaw-abc123"). If provided, only this session's interests are used for search_now. |
Structured output declared, but exposes no named fields.
No examples provided.
init_session Init Session ~349
Initialize a research session. Call this first to set up push channels and load context. Detects configured platforms, manages channels, and optionally loads previous research context. Returns session info for the AI client to present to the user. IMPORTANT for AI clients: - NEVER call external APIs (Zotero, webhooks, etc.) directly or generate scripts (PowerShell, curl, Python) to do so. Always use the built-in tools (collect, collect_to_zotero, send_push, etc.). Direct API calls will result in incomplete data and encoding issues. - If multiple platforms are detected and no `platform` is specified, the response will include `ask_platform` — you MUST ask the user which platform to use, then call init_session again with `platform=<user_choice>`. - If only one platform is configured, it is auto-selected. - The `send_push` tool also accepts a `platform` parameter, so the user can override per-push even after init.
| Name | Type | Req | Description |
|---|---|---|---|
| channel_action | string | – | "new" = create dedicated channel, "existing" = use configured channel, "auto" = use existing if available. |
| load_context | string | – | "yes" = auto-load previous research context, "no" = start fresh, "ask" = return context summary for user to decide. |
| platform | – | – | Preferred push platform ("telegram", "discord", "feishu", "wecom"). If None, auto-detects from configured env vars. |
| session_id | – | – | Session identifier (auto-generated if not provided). Use different IDs to isolate research vs daily topics. |
Structured output declared, but exposes no named fields.
No examples provided.
load_session_context Load Session Context ~63
Load previous research context into current session. Call this after init_session if user chose to load context. Returns accumulated keywords and summaries from interests.jsonl.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | – | – | If provided, only load context from this session. If None, load all previous context. |
Structured output declared, but exposes no named fields.
No examples provided.
manage_topics Manage Topics ~81
Manage research topic preferences.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | One of "list", "block", "unblock", "set_weight" |
| topic | – | – | Topic key (required for block/unblock/set_weight, e.g. "llm-news") |
| weight | – | – | New weight value (only for set_weight action, 0.0-1.0) |
Structured output declared, but exposes no named fields.
No examples provided.
pool_refresh Pool Refresh ~91
Refresh the paper search pool by querying 9 academic APIs. Call this when pool is exhausted or when adding a new research topic. Searches: OpenAlex, Semantic Scholar, PubMed, arXiv, Papers with Code, CrossRef, Europe PMC, bioRxiv, DBLP.
| Name | Type | Req | Description |
|---|---|---|---|
| topic | – | – | Optional single topic key to search (for new topics). If None, refreshes all topics. |
Structured output declared, but exposes no named fields.
No examples provided.
pool_status Pool Status ~24
Show current pool status: paper counts by status, scan day, topics searched.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
prepare_review Prepare Review ~83
Prepare the review prompt for today's scan batch. Returns a structured prompt listing candidate papers for the AI to review. The AI should respond with push/overflow/discard decisions in JSON format. If pool is exhausted, returns "POOL_EXHAUSTED" — call pool_refresh first.
| Name | Type | Req | Description |
|---|---|---|---|
| dual | boolean | – | Enable dual review mode (two reviewers each pick 3 papers) |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
prepare_summarize Prepare Summarize ~121
Generate a summarization prompt for unsummarized papers in today's batch. Returns a dict with: - prompt: the summarization prompt (structured fields to extract) - summarizer: who should process this prompt ("self", agent name, or API URL) - paper_count: how many papers need summarizing If summarizer is NOT "self", the calling agent should delegate this prompt to the specified agent or API instead of processing it directly. This can save significant token costs.
| Name | Type | Req | Description |
|---|---|---|---|
| custom_focus | string | – | Optional custom screening criteria to include |
Structured output declared, but exposes no named fields.
No examples provided.
rank_papers Rank Papers ~94
Score and rank papers using 4-factor weighted formula. Factors: relevance (0.55), recency (0.20), impact (0.15), novelty (0.10). Uses topic_prefs.json for relevance scoring and papers.jsonl for novelty detection.
| Name | Type | Req | Description |
|---|---|---|---|
| papers | array | yes | List of paper dicts (from search_papers) |
| top_n | integer | – | Return top N papers after ranking |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
search_papers Search Papers ~124
Search academic papers across 9 sources (OpenAlex, Semantic Scholar, PubMed, arXiv, Papers with Code, CrossRef, Europe PMC, bioRxiv, DBLP). Returns deduplicated, merged results sorted by cross-source hits + citation count. Each paper has: title, year, doi, authors, abstract, source, citation_count, etc.
| Name | Type | Req | Description |
|---|---|---|---|
| max_results | integer | – | Maximum number of results to return (default 10) |
| query | string | yes | Search query string (e.g. "LLM reasoning chain-of-thought") |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
send_push Send Push ~99
Format and send daily paper distill to a messaging platform. Supported platforms: telegram, discord, feishu (飞书/Lark), wecom (企业微信 webhook).
| Name | Type | Req | Description |
|---|---|---|---|
| date | string | yes | Date string in YYYY-MM-DD format |
| papers | array | yes | Papers to include in the push message |
| platform | string | – | Target platform - "telegram", "discord", "feishu", or "wecom" (default: telegram) |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
setup Setup ~67
Check setup status and guide first-time configuration. Call this FIRST when starting a new session. Returns setup state and instructions for the AI client on what to ask the user. If setup is complete, returns current config summary. If first run, returns step-by-step instructions for the AI to follow.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the Paper Distill MCP server?
Paper Distill MCP runs locally as a PyPI package, launched with uvx paper-distill-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 · paper-distill-mcp
claude mcp add eclipse-cj-paper-distill-mcp -- uvx paper-distill-mcp
What is the Paper Distill MCP server?
Paper Distill MCP is listed in the public MCP registry as io.github.Eclipse-Cj/paper-distill-mcp. Academic paper search across 11 sources with AI curation, ranked push, Zotero and Obsidian support. This page covers its PyPI package (paper-distill-mcp).
Is the Paper Distill MCP server safe to use?
Paper Distill MCP scores 76 out of 100 on VerifyMCP. 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 Paper Distill MCP server expose?
Paper Distill MCP exposes 19 tools: search_papers, rank_papers, filter_duplicates, generate_digest, send_push, and 14 more. Their descriptions and schemas cost roughly 2,280 tokens of context every time the server is loaded.
Is the Paper Distill MCP server still maintained?
Paper Distill MCP is still listed as active in the MCP registry. We last reached this channel on 4 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 Paper Distill MCP server under?
Paper Distill MCP declares the AGPL-3.0-only licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.