DeepStack: Independent analysis of the AI economy
RemoteAbout DeepStack: Independent analysis of the AI economy
DeepStack's MCP server lets clients query a publication's sourced analysis of disagreements about AI investment and infrastructure. It presents opposing cases, editorial calls and dated tests, without generating model output at request time.
Key features
- 01Search published disputes and topics
- 02Read full analysis of both sides
- 03Retrieve claims with dates and attribution
- 04Find tests and probabilities for calls
- 05Review resolved calls and results
- 06Look up entities and macro data
Use cases
- 01Comparing arguments about AI capex
- 02Finding evidence behind a company thesis
- 03Tracking dated tests and their outcomes
- 04Checking the strongest counterargument
MCP support
Provides eight read-only tools over Streamable HTTP for MCP clients to search and retrieve DeepStack's published analysis. The unauthenticated server returns sourced text from the publication's public API.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.deepstack.ltd/mcpclaude mcp add --transport http mcauduro0-deepstack https://mcp.deepstack.ltd/mcp{"mcpServers":{"mcauduro0-deepstack":{"type":"http","url":"https://mcp.deepstack.ltd/mcp"}}}Open in Cursor{"servers":{"mcauduro0-deepstack":{"type":"http","url":"https://mcp.deepstack.ltd/mcp"}}}Open in VS Code{"mcpServers":{"mcauduro0-deepstack":{"type":"http","url":"https://mcp.deepstack.ltd/mcp"}}}{"mcpServers":{"mcauduro0-deepstack":{"serverUrl":"https://mcp.deepstack.ltd/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEDeepStack MCP server
The Model Context Protocol server behind DeepStack, an independent publication on the money behind AI. For each argument about AI capital (capex, credit, power, chips, the labs), DeepStack publishes the strongest case on each side with dated, sourced claims, takes a side (the DeepStack Call), and writes down the test that will settle it: the event, the date, the rule, and the probability the Call gave "yes" before the date. When the date comes, the result is published, whichever way it went.
This server lets any MCP client read that record.
- Endpoint:
https://mcp.deepstack.ltd/mcp(Streamable HTTP, JSON-RPC 2.0) - Authentication: none. Read-only. Free.
- Registry:
io.github.mcauduro0/deepstackin the official MCP Registry - Docs: deepstack.ltd/mcp
Every answer is the published analysis as text, cites the canonical deepstack.ltd URL of each item it names, and ends with "Analysis and opinion, not investment advice." No model runs at request time.
Tools
| Tool | Use it when the user asks |
|---|---|
deepstack_search | where informed investors disagree on a topic, a company, a person or a question |
deepstack_story | for one Part read in full: the question, both sides, the Call, what would change it, the next dated test |
deepstack_sides | for the bull and bear case, or who disagrees with a thesis, with every claim attributed and dated |
deepstack_docket | what will settle a dispute and when: the dated tests, their rules and the Call's probability |
deepstack_results | what resolved and how the Call fared |
deepstack_entity | what the voices argued about a company or what a person argued |
deepstack_tape | for the macro figures the notes are tested against, each with its producer and date |
deepstack_counter | for the strongest published case against a thesis or a claim |
All tools carry readOnlyHint: true.
Connect a client
Configuration files for each client are in clients/.
Claude (claude.ai and the desktop app). Settings, Connectors, Add custom connector. Name it DeepStack and use the URL https://mcp.deepstack.ltd/mcp, with no OAuth.
Claude Code
claude mcp add --transport http deepstack https://mcp.deepstack.ltd/mcp
Cursor, Windsurf and other editors (mcp.json)
{ "mcpServers": { "deepstack": { "url": "https://mcp.deepstack.ltd/mcp" } } }
VS Code (.vscode/mcp.json)
{ "servers": { "deepstack": { "type": "http", "url": "https://mcp.deepstack.ltd/mcp" } } }
Any client, by hand
curl -s https://mcp.deepstack.ltd/mcp -H 'content-type: application/json' -H 'accept: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"deepstack_docket","arguments":{}}}'
Limits and what is kept
- 60 requests per minute per session (the
Mcp-Session-Idthatinitializeissues), else per address; 30initializecalls per minute per address. - The questions asked through the tools are kept as text, with the date, the tool, the number of results and the name the calling program gives itself, to learn which disputes readers ask about. No address, user agent or cookie is kept. Details: deepstack.ltd/privacy.
- Terms: deepstack.ltd/terms.
How it works
A Cloudflare Worker in plain JavaScript (ES modules, no bundler, no npm dependencies). It reads DeepStack's public static API at https://deepstack.ltd/api/v1/ with a ten-minute cache and answers from it. The same JSON is open to any program; this server makes it answerable in a conversation.
src/index.js router, CORS, cache, rate limit, the questions store
src/mcp.js JSON-RPC (initialize, ping, tools/list, tools/call) and the eight tools
src/lib.js pure helpers: keyword index and ranking, excerpts, formatting
src/stats.js aggregates for the owner's admin route
src/events.js per-day counts of the site's named controls
schema.sql the D1 tables
server.json the MCP Registry manifest
Run the tests with Node 20 or later:
npm test
To run your own copy you need a Cloudflare account: create a D1 database, put its id in wrangler.toml, apply schema.sql, set the ADMIN_TOKEN secret, and npx wrangler deploy. Point API_BASE at any host that serves the same JSON shape.
This repository mirrors the server that runs at mcp.deepstack.ltd. The publication itself, its data pipeline and its editorial process are not part of it.
License
The code is MIT-licensed (see LICENSE). The content the server returns belongs to DeepStack and is governed by the terms.
Analysis and opinion, not investment advice.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.