MCP.Market

Torus MCP server

by sekhar14·io.github.sekhar14/torus·v0.4.1·1 stars

Stock research memory for Claude: theses, sourced claims and SEC filing alerts in a local graph

A92/100grade A
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

1 stars273 downloads/wk

Reviews

Write one

Nobody has reviewed Torus yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Torus tools (45, 6 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • add_event

    Record an event and raise alerts on theses it may affect (through the companies involved and their suppliers, customers and competitors).

  • alert_stats

    How useful alerts have been: verdicts, and the share judged related (precision) by source, form, hops and materiality.

  • audit

    Health check of the research graph: expired or thinly sourced assumptions, theses past their horizon or gone stale, claims that may conflict, unconfirmed starter links, orphans. Each finding suggests a fix.

  • brief

    One-call briefing at the start of a turn: spots known companies in `text`, recalls prior theses, claims, open alerts and ruled-out ideas about them, and returns the graph digest.

  • complete_distillation

    Finish a leased distillation job (or hand it back if it failed).

  • complete_mapping

    Finish a leased mapping job (or hand it back if it failed).

  • digest

    What happened in the research over the last days: new alerts by thesis, thesis status and confidence changes, theses coming due, audit counts, scorecard moves and activity. ``markdown`` is ready to show.

  • filing_diff

    What changed in a section of a company's latest filing against the previous one of the same form: new, dropped and reworded sentences.

  • filing_text

    Read a company's SEC filing as text, by section, from EDGAR (cached). Long sections come in pages: pass `next_offset` back as `offset`.

  • find_paths

    How two entities are connected, e.g. ASML -SUPPLIES-> TSMC -SUPPLIES-> AMD. Shortest and most confident paths first.

  • get_entity

    Resolve an entity and list its current relations.

  • impact

    Dry run: which theses would an event on these entities affect, and why? Records nothing.

  • list_alerts

    Alerts raised by events on theses, highest score first. Each shows how its score was built: graph score x event materiality x (1 + trigger match).

  • list_watches

    What the watchers follow: the watchlist, open-thesis entities, feeds.

  • merge_entities

    Fold a duplicate entity into the one to keep; its links move over.

  • neighbors

    The entity's neighbourhood: companies within `hops` links (suppliers, customers, competitors...), the links among them, and theses about them.

  • next_distillation

    Lease the oldest research session waiting to be distilled into the graph.

  • next_mapping

    Lease the next onboarded company to map from its annual report. Until `complete_mapping`, links you record are marked as curator links.

  • onboard

    Start covering companies: add them, watch their filings, suggest starter packs, and queue a mapping job for each (run by the company-mapper subagent, which reads their annual reports and records suppliers, customers and competitors).

  • open_explorerwrite action

    Write the interactive graph explorer HTML file (under TORUS_HOME/explorer.html) and open it in the user's browser.

  • recall

    Prior theses, claims and rejected hypotheses about entities and/or a question.

  • recent_records

    What the most recent research sessions recorded, newest first, and which records can still be undone.

  • record_claim

    Record a finding. Facts and metrics need evidence_ids.

  • record_evidence

    Record a source. Re-recording the same URI returns the existing record.

  • record_rejected_hypothesis

    Record an idea that was checked and ruled out, so it isn't re-explored.

  • record_relation

    Link two entities, e.g. TSMC SUPPLIES NVIDIA. Re-recording an existing link updates it (confidence, backing claim, dates) instead of duplicating it.

  • record_thesis

    Record a conclusion and the claims it rests on.

  • resolve_alert

    Judge an alert after reading the event and the thesis's claims; the thesis is updated accordingly and the change logged with the alert.

  • retract_claim

    Withdraw a claim that turned out to be wrong (kept in history).

  • scorecard

    How tracked theses have done against their benchmarks, their outcomes, and calibration: did the user's confidence match how often they were right?

  • search

    Keyword search over current claims, evidence and theses.

  • seed_starter_pack

    Add a curated starter pack of companies and supplier/competitor links. Never overrides links research recorded.

  • set_thesis_outcome

    Record whether a thesis turned out right, wrong or unclear (overrides the automatic outcome; used for calibration).

  • supersede_claim

    Correct a claim: the old version stays in history, the new one is current.

  • thesis_memowrite action

    Write a thesis up as a memo (Markdown and a standalone HTML page): what it rests on with sources and quotes, triggers, events and verdicts, ruled-out ideas and history. Saved under TORUS_HOME/memos.

  • thesis_weak_points

    Where a thesis is weakest: thin or expiring assumptions, strong supplier or customer dependencies it never mentions, triggers that can't fire on events, and opposing views already in the graph. Input for /torus:challenge.

  • timeline

    Chronological claims and thesis changes for one entity.

  • track_thesiswrite action

    Put a thesis on the scorecard: its return against a benchmark from an entry price and date, in the direction of its stance.

  • undo_records

    Revert records the user doesn't want: claims are retracted (corrections go back to the earlier version), theses the session created are archived, links retired, ruled-out ideas withdrawn. History keeps everything.

  • unwatchwrite action

    Remove a company from the explicit watchlist.

  • update_thesiswrite action

    Revise a thesis: status, confidence, the claims it rests on, and its triggers, in one atomic step. Everything is kept in its history.

  • upsert_entitywrite action

    Create an entity (or merge into the one with the same canonical_key).

  • watch

    Watch a company: its new SEC filings become events (on the next `torus watch run`). Subjects of open theses are watched automatically.

  • what_changed

    Everything recorded or revised across the graph since a point in time.

  • whatif

    What if this happened? Which theses would it reach, through which links, and would it raise alerts. Records nothing.

Public scan report

scanner v0.1.10 · 2026-10-24 · same rubric, same numbers if you re-run it

no findings
  • Code scan78 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Torus compares

Against every graded Finance MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 95% of 1,675 Finance servers
Tools
45
the typical Finance server has 9
Tools that change things
13%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 65% of 906 Finance servers
Downloads a week
273
more than 86% of 379 Finance servers with a package

What its tools let an agent do: 36 read · 2 create · 7 change

Install Torus in Claude Code, Cursor or VS Code

claude mcp add torus -- uvx torus-kg
Add to Cursor

What the publisher says

From the Torus repository's README, as published. We do not edit it. Read it on GitHub

Torus

<!-- mcp-name: io.github.sekhar14/torus -->

Stock research memory for Claude Code, Claude Desktop and Codex. Torus gives Claude a memory for your equity research. Before it answers, Claude sees what you already know about a company: your theses, the sourced facts behind them, its suppliers, customers and competitors, and the ideas you ruled out. New research builds on the old, and every new fact is saved with its source. When a new SEC filing or news story threatens a thesis, Torus warns you: on your desktop as it happens, and in a daily or weekly digest by email, Slack, Discord or ntfy.

Ask Claude "Is NVIDIA still supply-bound?" and it starts from what you already concluded, not from scratch. Torus keeps:

  • the companies you cover and how they connect: suppliers, customers, competitors
  • claims about them, each tied to its source (a 10-K, an earnings call, an article)
  • your investment theses: bullish or bearish, the claims they rest on, and what would break them
  • ideas you ruled out, so you don't research them again

When a 10-K, 10-Q, 8-K or news item lands, Torus works out which of your theses it touches, through which supplier or customer link, and how much it matters. It also keeps the research honest (what's gone stale, what rests on one source, what a skeptic would say) and tracks how your calls did against the market.

Built for analysts, portfolio managers and serious individual investors.

and cheaper Haiku subagents do the bookkeeping.

  • Your model, your subscription. Torus never calls an LLM itself. Claude does the reasoning,

TORUS_HOME).

  • Local-first. Your research stays in one SQLite file under ~/.torus (override with

what you thought on any past date. Nothing is deleted: corrections are new versions.

  • Time-aware. Every fact records when it was true and when you believed it, so you can ask

Torus is a research memory, not financial advice. See CHANGELOG.md for what's in each release.

Pick your app

Torus works in three apps. All of them share one graph on your machine, so you can research in one and pick up in another.

Claude Desktop

pip install torus-kg
torus setup

The package is called torus-kg on PyPI; the command it installs is torus. torus setup asks for the email the SEC requires, downloads the SEC ticker list, adds Torus to Claude Desktop's settings (it keeps a .bak copy and leaves your other servers alone), and schedules the filing watchers. Restart Claude Desktop, then try the Onboard companies prompt from the "+" menu with a few tickers.

Codex

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Torus: common questions

Is Torus MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Torus safety report
How do I install Torus?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Torus need an API key?
No secret keys are declared. It reads 3 settings from the environment.
Is Torus maintained?
The last commit was in the last day (2026-10-24). The latest release is v0.4.1.
What can I use instead of Torus?
Servers from other publishers that do the same job: Tapetide - Indian Stock Market MCP server, RoboSystems MCP server and HKEx Filings MCP server. Compare all Torus alternatives.
How does Torus compare with other Finance MCP servers?
safety score 92/100 (higher than 95% of 1,675 Finance servers); tools 45 (the typical Finance server has 9); tools that change things 13% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Torus

Same job from other publishers: the closest match first, then the best rated.

All Torus alternatives →
  • Tapetide - Indian Stock Market MCP
    55 tools for Indian stock markets — NSE & BSE quotes, screener, filings, FII/DII, options
    A
  • RoboSystems
    Accounting knowledge graphs: SEC XBRL filings, QuickBooks ledgers, reports and forecasts over MCP.
    A
  • HKEx Filings
    Live HKEx (Hong Kong Stock Exchange) regulatory filings for AI agents.
    A
  • EdgeDepth Research
    Test crypto-perpetual claims using recorded counts, baselines, and replay.
    A
  • Pseudolife Memory
    Persistent memory for MCP-compatible agents: memory bank, fact cortex, dreams, graph.
    A