Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Search, read, bet on, create, and resolve prediction markets on Manifold.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
MANIFOLD_API_KEYValues marked secret are keys to your account. Never share them or paste them into a chat.
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Download the maker’s .mcpb file
The link goes to the maker’s own file; we do not host or repackage it. Open the file and Claude Desktop installs it.
Run this in your terminal
Fill in the empty values before running it.
Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
The registry name was verified with the GitHub account jbeshir, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: MANIFOLD_API_KEY
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.0.2) reached the registry 12 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB on your computer.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
An MCP server for interacting with Manifold Markets, a prediction market platform. Provides 18 tools covering market discovery, trading (bets and limit orders), market management (creation, resolution, comments, liquidity), and portfolio analytics. Communicates over stdio and works with any MCP-compatible client such as Claude Desktop or Claude Code.
| Variable | Required | Description |
|---|---|---|
MANIFOLD_API_KEY | Yes | Your Manifold Markets API key |
MANIFOLD_API_URL | No | Custom API URL (default: https://api.manifold.markets) |
Requires Go 1.27.3+.
go install github.com/jbeshir/mcp-servers/manifold/cmd/manifold-mcp@latest
Download from Releases.
docker build -t manifold-mcp ./manifold
docker run -e MANIFOLD_API_KEY= manifold-mcp
{
"mcpServers": { "manifold": { "command": "/path/to/manifold-mcp", "env": { "MANIFOLD_API_KEY": " " } } } }
claude mcp add manifold -- env MANIFOLD_API_KEY=<your-key> /path/to/manifold-mcp
| Tool | Description |
|---|---|
search_markets | Search markets by keyword and filters |
get_market | Get full market details including answers and description |
get_user | Get a user's profile by username |
get_me | Get the authenticated user's profile |
list_bets | List bets with optional filters |
get_comments | Get comments on markets |
get_positions | Get user positions for a specific market |
| Tool | Description |
|---|---|
place_bet | Place a bet or limit order (supports dryRun) |
sell_shares | Sell shares in a market |
cancel_bet | Cancel a pending limit order |
| Tool | Description |
|---|---|
create_market | Create a new market (binary, multiple choice, or numeric) |
resolve_market | Resolve a market you created |
close_market | Close a market or change its closing time |
add_comment | Comment on a market |
add_liquidity | Add mana liquidity to a market |
send_mana | Send mana to other users |
| Tool | Description |
|---|---|
get_baseline | Get deterministic baseline probability for a market at a past time (default: 24h) |
get_portfolio_pnl | Get full portfolio P&L summary with 24h changes for all positions |
place_bet with a limitProb parameter to create one.place_bet tool supports dryRun=true to simulate a bet without executing it, showing what the outcome and cost would be.graph LR
Client["MCP Client (Claude Desktop, Claude Code)"] Server["manifold-mcp MCP Server"] HTTP["HTTP Client"] API["Manifold Markets REST API"]
Client -- "JSON-RPC over stdio" --> Server Server --> HTTP HTTP -- "HTTPS + API key auth" --> API
The server has three internal layers:
tools.go (read operations), tools_trading.go (trading), and tools_manage.go (market management).Authorization header), JSON serialization, and error handling.A typical trading workflow: search for a market, inspect it, simulate a bet, then execute.
sequenceDiagram
participant C as MCP Client participant S as manifold-mcp participant A as Manifold API
C->>S: search_markets(term: "AI") S->>A: GET /v0/search-markets?term=AI A-->>S: Market list S-->>C: Formatted results
C->>S: get_market(marketId: "abc123") S->>A: GET /v0/market/abc123 A-->>S: Full market details S-->>C: Question, probability, answers
C->>S: place_bet(contractId, amount, outcome, dryRun: true) S->>A: POST /v0/bet (dryRun) A-->>S: Simulated bet result S-->>C: Expected shares, probability change
C->>S: place_bet(contractId, amount, outcome) S->>A: POST /v0/bet A-->>S: Executed bet S-->>C: Bet confirmation