Sibyl — Deep Research MCP

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/chriswu727-sibyl

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools

9 read · 3 write · 1 delete · 7 not yet classified

Secrets

None asked for

Install scripts

None found

Runs as

Python package

Tools (20)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• analyze

  Analyze provided text with a specific question using LLM. Takes any text (article, report, data, transcript) and answers a specific question about it using the configured LLM provider. Useful for follow-up analysis on content from read_url() or research(). Returns a structured analysis with clear reasoning and evidence from the text. Args: text: The text content to analyze (article, report, data — up to 5000 chars) question: The specific question to answer about the text (e.g. "What are the main risks mentioned?" or "Summarize the key arguments for and against")

• assess_research

  Record host judgment for one planned question; does not call a model. Status: supported, disputed, or unresolved. Cite stable passage IDs, not changing source numbers. Inspect methods, freshness, source independence, and counterevidence first. Unknown references and stale revisions fail. Reviews preserve cited evidence in the report window, but do not prove truth. For remaining gaps, supply up to four focused follow_up_queries. The plan recommends these before generic queries and omits already completed searches.

• cancel_research

  Cancel research and retain evidence, or explicitly delete its local checkpoint. Deleting a job does not delete previously exported report files.

• chart

  Generate a price history line chart for one or more financial symbols. Fetches historical price data from Yahoo Finance and creates a professional multi-line chart saved as PNG. The chart is automatically attached to the current research report and embedded in PDF output when save_report() is called. Supports stocks, ETFs, indices, crypto, and commodities. Args: symbols: Comma-separated ticker symbols (e.g. "NVDA,AMD,INTC" for stocks, "BTC-USD,ETH-USD" for crypto, "GC=F" for gold) period: Historical time period — "1mo", "3mo", "6mo", "1y", "2y", "5y" (default: "1y") title: Custo…

• compare

  Generate a structured comparison table for 2-5 items. Researches each item and produces a side-by-side markdown table with key metrics, strengths, weaknesses, and a bottom-line recommendation. Args: items: Comma-separated items to compare (e.g. "NVDA,AMD,INTC" or "React,Vue,Angular") query: Context for the comparison (e.g. "for AI/ML workloads" or "for a startup in 2026")

• complete_research

  Save a host-authored report against a current evidence revision. Summary and findings must cite selected [Source N] numbers from get_research. Distinguish facts from inferences; disclose unresolved questions. This checks citation targets, NOT semantic support. Completion makes the report immutable. New host jobs require per-question reviews and counterevidence investigation. allow_incomplete preserves unmet gates as limitations and report.status=partial; the completed job is finalized, not necessarily complete in research coverage.

• continue_research

  Retrieve a focused query for a host job, or explicitly resume an autonomous job. Autonomous resume omits query, reuses saved evidence and budgets, and can incur additional model charges. It may regenerate unfinished draft sections. Host attempts link to question_id. Purpose: explore, counterevidence, or follow_citation. URL reads share the job budget and persist exact passages; follow_citation requires a parent passage ID. This parent link is host-declared, not an automatically verified hyperlink. Explain why this round is needed in rationale. Each round records its prior gaps and evidence re…

• fetch_market_data

  Fetch real financial/stock/ETF data from Yahoo Finance. Returns current price, trend, moving averages, 52-week range, and % change. Args: symbols: Comma-separated ticker symbols (e.g. "AAPL,MSFT,SPY" or "XIU.TO,XRE.TO" for Canadian ETFs) period: Time period — "1mo", "3mo", "6mo", "1y", "2y", "5y" (default: 1y) Common symbols: US: SPY (S&P 500), QQQ (Nasdaq), DIA (Dow), VTI (total market) Canada: XIU.TO (TSX 60), XRE.TO (REIT), XIC.TO (composite) Crypto: BTC-USD, ETH-USD Commodities: GC=F (gold), CL=F (oil)

• gather_bundle

  Return a structured, keyless SourceBundle without synthesizing an answer. This is the programmatic form of gather_sources, intended for agents and pipelines that need stable evidence identifiers and retrieval provenance. Passage/source relevance defaults to the dependency-free lexical_v1 ranker. FlashRank is optional and falls back to lexical_v1 with an explicit diagnostic. Source quality remains null until a separate quality evaluator computes it. Follow diagnostics.recommended_action; only "synthesize" permits synthesis. Args: query: One focused search query max_sources: How many s…

• gather_evidence

  Run a bounded evidence loop while leaving planning and synthesis to the host. Start with question only. For a complex question, use the returned loop_id and call this tool again with one atomic query. Continue according to next_action. When the returned steps cover the question, call with finish=true and list the synthesis-ready E-step IDs that support the answer. Only status="ready" permits synthesis. Loops expire after ten minutes and allow at most four retrieval calls. Args: question: Original research question; use only when starting a loop loop_id: Existing loop identifier for a…

• gather_sources

  Keyless web retrieval: search + scrape + dedup, returning the top FULL-TEXT sources for a query WITHOUT writing an answer — so YOU (the calling model) read the evidence and reason over it yourself. Use this to research a question: call it several times with different focused sub-queries, read the numbered [Source N] blocks it returns, cross-reference them, then write the answer yourself with citations. If the sources don't contain the answer, gather more or say you don't know — do not guess. No API key required. Args: query: One focused search query (issue several calls for a multi-part …

• get_research

  Read progress, evidence, current citation numbering and report; omit ID to list jobs. Retrieval coverage is heuristic, not factual proof. Semantic support in host-authored reports is not independently verified. Read limitations.

• quick_search

  Quick web search without deep analysis. Returns raw search results. Args: query: What to search for max_results: Maximum number of results (default 5)

• read_url

  Read and extract clean text content from a URL. Fetches the page, strips navigation/scripts/ads, and returns the main article or body text; optional text-PDF input preserves page markers and extraction limitations. Useful for reading a specific source in detail before or after running research(). Returns the page title, URL, and up to 8000 characters of clean text. Enforces public-network policy and a bounded request deadline. Args: url: The full URL to read (e.g. "https://www.reuters.com/article/...")

• research

  Run a deep research cycle on any topic. Searches the web, reads multiple sources, and synthesizes a comprehensive report with findings, analysis, and optionally predictions. Args: query: The research question (e.g. "What's the outlook for Canadian housing market in 2026?") depth: 1=focused research, 2=decomposition and coverage review, 3=deeper analysis and uncertainties language: Output language. "auto" (match query language), "en", "zh" (Chinese), or any language name fast: Skip the review/refine pass for ~20% faster results with slightly less polish verify: Audit repor…

Signals

Stars

2

Forks

0

Open issues

0

Weekly downloads

148

Last commit

Oct 22, 2026 (6 days ago)

Last release

Oct 22, 2026 (6 days ago)

Last package publish

Jul 15, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.chriswu727/sibyl

Version

0.4.0b1

Auth

No auth

Packages

pypi sibyl-research

License

MIT

Repository

github.com/chriswu727/sibyl

Website

yichenwu.dev/projects/sibyl

First seen

Oct 24, 2026

Last checked

Oct 25, 2026

Source

Official MCP Registrygithub-graphql