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.

Paper Distill MCP

PYPI · PAPER-DISTILL-MCP · SCANNED SEP 20

Academic paper search across 11 sources with AI curation, ranked push, Zotero and Obsidian support.

Available components

−15 this week 66 Trust /100
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 hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 4 of 49 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency35
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • License check failed: the license (GNU Affero General Public License v3) isn't a recognized OSI-approved license. See how to fix → Fail
  • Actively maintained (last published 184 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 2347 tokens (~106/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 Management87
  • Stability observed for 26 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
Install

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

# add to Claude Code
claude mcp add eclipse-cj-paper-distill-mcp -- uvx paper-distill-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "eclipse-cj-paper-distill-mcp": {
      "command": "uvx",
      "args": [
        "paper-distill-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "eclipse-cj-paper-distill-mcp": {
      "command": "uvx",
      "args": [
        "paper-distill-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add eclipse-cj-paper-distill-mcp -- uvx paper-distill-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "eclipse-cj-paper-distill-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "paper-distill-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add eclipse-cj-paper-distill-mcp --command uvx --arg paper-distill-mcp
# ~/.hermes/config.yaml
mcp_servers:
  eclipse-cj-paper-distill-mcp:
    command: "uvx"
    args: ["paper-distill-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "eclipse-cj-paper-distill-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "paper-distill-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add eclipse-cj-paper-distill-mcp -t stdio -c uvx -a paper-distill-mcp
// mcp.json
{
  "mcpServers": {
    "eclipse-cj-paper-distill-mcp": {
      "command": "uvx",
      "args": [
        "paper-distill-mcp"
      ]
    }
  }
}
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 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 17 Sept 26 +1
    • Stability: 0.97 → pass security
  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 −15
    • Malware scan: pass → unverified security
  • 13 Sept 26 +16
    • Malware scan: unverified → pass security
  • 11 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 10 Sept 26 +1
    • Stability: 0.97 → pass security
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 20 Sept 2026 · Analysed pypi/paper-distill-mcp@0.2.4

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

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 49 packages
Packages resolved 49
Stale 3
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 19 exposed · ~2,301 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
add_topic ~109

Add a research topic for paper search.

NameTypeReqDescription
keystringyesShort identifier (e.g. "llm-reasoning", "rag-retrieval"), lowercase with hyphens
keywordsarrayyesSearch keywords for this topic (3-5 recommended)
labelstringyesHuman-readable name (e.g. "LLM Reasoning")
weightnumberPriority weight 0.0-1.0 (default 1.0 = highest priority)

Structured output declared, but exposes no named fields.

No examples provided.

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).

NameTypeReqDescription
obsidian_modestring"none" (Zotero only), "summary" (with AI summary note), or "template" (empty template for user notes)
paper_indicesstringyesComma-separated 1-based indices (e.g. "1,3")
NameTypeReqDescription
resultstringyes

No examples provided.

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.

NameTypeReqDescription
paper_idsarrayyesList of paper DOIs or IDs to add to Zotero
NameTypeReqDescription
resultarrayyes

No examples provided.

configure ~326

Update pipeline configuration. All parameters are optional — only provided values are changed.

NameTypeReqDescription
custom_focusCustom screening criteria (e.g. "prefer clinical trials over reviews")
paper_count_mode"at_most", "at_least", or "exactly"
paper_count_valueNumber of papers per push (e.g. 6)
picks_per_reviewerPapers each reviewer selects per scan (default 5)
review_mode"single" (one AI reviews) or "dual" (two AIs review independently)
scan_batchesNumber of scan batches per pool cycle (default 2, pool is reviewed over batches+1 days)
site_deploy_hookVercel deploy hook URL for auto-deploying paper library website
site_repo_pathLocal path to the paper library site repo (for pushing digest JSON)
summarizerWho 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_impactRanking weight for citation impact (default 0.15)
w_noveltyRanking weight for novelty/unseen (default 0.10)
w_recencyRanking weight for publication recency (default 0.20)
w_relevanceRanking weight for topic relevance (default 0.55)

Structured output declared, but exposes no named fields.

No examples provided.

filter_duplicates ~35

Remove papers already pushed (by DOI match against papers.jsonl).

NameTypeReqDescription
papersarrayyesList of paper dicts to filter
NameTypeReqDescription
resultarrayyes

No examples provided.

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.

NameTypeReqDescription
is_finalbooleanTrue for final review (no discard allowed, only push/overflow)
selectionsstringyesJSON string with review decisions, e.g. '[{"index": 1, "action": "push", "tldr": "..."}, ...]'
NameTypeReqDescription
resultstringyes

No examples provided.

generate_digest ~70

Generate all daily output files (pushes.jsonl, papers.jsonl, Astro site JSON, Obsidian notes).

NameTypeReqDescription
datestringyesDate string in YYYY-MM-DD format
papersarrayyesFinal selected papers with annotations
topicsOptional topics data for research note generation

Structured output declared, but exposes no named fields.

No examples provided.

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).

NameTypeReqDescription
markdown_textstringyesMarkdown text containing research context (e.g. from another AI's summary)
search_nowbooleanIf True, also run a paper search using extracted keywords
session_idOptional 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 ~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.

NameTypeReqDescription
channel_actionstring"new" = create dedicated channel, "existing" = use configured channel, "auto" = use existing if available.
load_contextstring"yes" = auto-load previous research context, "no" = start fresh, "ask" = return context summary for user to decide.
platformPreferred push platform ("telegram", "discord", "feishu", "wecom"). If None, auto-detects from configured env vars.
session_idSession 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 ~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.

NameTypeReqDescription
session_idIf 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 ~81

Manage research topic preferences.

NameTypeReqDescription
actionstringyesOne of "list", "block", "unblock", "set_weight"
topicTopic key (required for block/unblock/set_weight, e.g. "llm-news")
weightNew weight value (only for set_weight action, 0.0-1.0)

Structured output declared, but exposes no named fields.

No examples provided.

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.

NameTypeReqDescription
topicOptional 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 ~45

Show current pool status: paper counts by status, scan day, topics searched. Returns: Dict with total, by_status, scan_day, total_scan_days, exhausted, etc.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

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.

NameTypeReqDescription
dualbooleanEnable dual review mode (two reviewers each pick 3 papers)
NameTypeReqDescription
resultstringyes

No examples provided.

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.

NameTypeReqDescription
custom_focusstringOptional custom screening criteria to include

Structured output declared, but exposes no named fields.

No examples provided.

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.

NameTypeReqDescription
papersarrayyesList of paper dicts (from search_papers)
top_nintegerReturn top N papers after ranking
NameTypeReqDescription
resultarrayyes

No examples provided.

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.

NameTypeReqDescription
max_resultsintegerMaximum number of results to return (default 10)
querystringyesSearch query string (e.g. "LLM reasoning chain-of-thought")
NameTypeReqDescription
resultarrayyes

No examples provided.

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).

NameTypeReqDescription
datestringyesDate string in YYYY-MM-DD format
papersarrayyesPapers to include in the push message
platformstringTarget platform - "telegram", "discord", "feishu", or "wecom" (default: telegram)
NameTypeReqDescription
resultstringyes

No examples provided.

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.

Common questions

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 66 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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 2,301 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 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.