MCP.Market

Situationatlas MCP server

by situationatlas.com·com.situationatlas/mcp·v0.1.0

AI-summarized filings from 7 markets with special-situations screens, for research agents

C58/100grade C
What users say
No reviews yet
Be the first
Safety scan
C58/100

full report

Adoption
New

14 downloads/wk

Reviews

Write one

Nobody has reviewed Situationatlas yet.

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

Situationatlas tools (13, 5 write)

write = sends, deletes, buys or posts

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

  • add_monitor_ticker

    Add a ticker to a monitor group, with optional research notes.

  • create_dealwrite action

    Create a deal (investment thesis tracker). Required: companyName, status (e.g. "researching", "active", "passed").

  • create_monitor_groupwrite action

    Create a custom monitor group (a named watchlist).

  • filings_updates

    Resumable polling cursor: returns filings oldest-first from `since`, plus a cursor. First call: pass since=YYYY-MM-DD. Later calls: pass the returned cursor to receive only NEW filings. The canonical daily-briefing loop for agents.

  • get_deal

    Fetch one deal with thesis, notes, prices, and document list.

  • get_filing

    Fetch one filing by id, with full AI analysis.

  • list_deals

    List your tracked deals (investment theses/positions), newest first.

  • list_monitor_groups

    List the 33 predefined special-situations monitor groups (by category, with filing-filter configs) plus your custom groups.

  • list_monitor_tickers

    List tickers in a monitor group (predefined or custom).

  • remove_monitor_tickerwrite action

    Remove a ticker from a monitor group.

  • search_filings

    Search AI-summarized filings (SEC 8-Ks, Form 4 insider purchases, or Japan TDnet). Returns newest-first with analysis text and AI tags. Use category for special-situations screens (spinoffs, distressed, activism, buybacks, ma, privatizations, oddlot_tenders, ...).

  • update_dealwrite action

    Partially update a deal (any create_deal field).

  • update_monitor_tickerwrite action

    Update the notes or company name on a monitor-group ticker.

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

no findings
  • Code scan4 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 qualitystatic API keys via environment variables6/15
  • Maintenancerepository not readable: repo not found3/15
  • Maintainer identityverified namespace with website, no repo4/10
Overall 58/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Situationatlas compares

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

Safety score
58/100
higher than 13% of 48,255 servers
Tools
13
the typical server has 7
Tools that change things
38%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
14
more than 4% of 12,191 servers with a package

What its tools let an agent do: 7 read · 3 create · 2 change · 1 delete

Install Situationatlas in Claude Code, Cursor or VS Code

Runs npx -y @situationatlas/mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcp -- npx -y @situationatlas/mcp
Add to Cursor

Situationatlas: common questions

Is Situationatlas MCP server safe?
With care: it is graded C, so read the findings first (58/100). Read the Situationatlas safety report
How do I install Situationatlas?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Situationatlas need an API key?
Yes. The registry entry asks for SITUATION_ATLAS_API_KEY.
Is Situationatlas maintained?
The latest release is v0.1.0.
How does Situationatlas compare with other MCP servers?
safety score 58/100 (higher than 13% of 48,255 servers); tools 13 (the typical server has 7); tools that change things 38% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.