Other · Local MCP server
Kalshi Prediction Markets
MCP server for Kalshi prediction markets: native RSA-PSS auth, rate limiting, demo/prod safety.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.cejor6/kalshi-mcp-server- Version
- 0.1.8
- Status
- Active
- Category
- other
- Transport
- stdio (local process)
- Package
- PyPI, OCI image (Docker)
- Published
- 2026-05-31
- Updated
- 2026-05-31
- Publisher
- cejor6 (GitHub)
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/cejor6) · how
- Repository
- github.com/cejor6/kalshi-mcp-server
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | kalshi-mcp-server | 0.1.8 | stdio |
| OCI image (Docker) | ghcr.io/cejor6/kalshi-mcp-server:0.1.8 | - | stdio |
How to connect Kalshi Prediction Markets
Kalshi Prediction Markets runs locally from a Python package published to PyPI: kalshi-mcp-server version 0.1.8. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx kalshi-mcp-server. It reads these environment variables: KALSHI_API_KEY_ID (required), KALSHI_PRIVATE_KEY_PATH, KALSHI_PRIVATE_KEY_PEM (secret), KALSHI_ENV, KALSHI_ALLOW_PROD and KALSHI_TRADING_ENABLED; set them in the client's configuration for this server.
Kalshi Prediction Markets runs locally from a container image in an OCI registry such as Docker Hub or GitHub Container Registry: ghcr.io/cejor6/kalshi-mcp-server:0.1.8. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Docker or another OCI container runtime; started with docker run - the usual command is docker run -i --rm -e KALSHI_API_KEY_ID -e KALSHI_PRIVATE_KEY_PEM -e KALSHI_ENV -e KALSHI_ALLOW_PROD -e KALSHI_TRADING_ENABLED ghcr.io/cejor6/kalshi-mcp-server:0.1.8. It reads these environment variables: KALSHI_API_KEY_ID (required), KALSHI_PRIVATE_KEY_PEM (secret), KALSHI_ENV, KALSHI_ALLOW_PROD and KALSHI_TRADING_ENABLED; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"kalshi-mcp-server": {
"command": "uvx",
"args": [
"kalshi-mcp-server"
],
"env": {
"KALSHI_API_KEY_ID": "<value>",
"KALSHI_PRIVATE_KEY_PATH": "<value>",
"KALSHI_PRIVATE_KEY_PEM": "<secret>",
"KALSHI_ENV": "<value>",
"KALSHI_ALLOW_PROD": "<value>",
"KALSHI_TRADING_ENABLED": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More other servers
| Server | Runs |
|---|---|
| KaidnExplain fraud verdicts with evidence, surface account rings, and see who has burned other operators. | Local · stdio |
| KaironBuild prospecting lists from buying signals, enrich them, and run LinkedIn outreach. | Remote · HTTPLive check: sign-in required |
| Kairos Relationship MemoryFree MCP: relationship_memory validate, store (local), retrieve - portable interlocutor cards v1. | Remote · HTTPLive check: ✗ no handshake |
| KaitenManage Kaiten spaces, boards, cards, comments, and tags with compact MCP responses. | Local · stdio |
| Kanbai - public project templates and SOPsRead-only access to Kanbai's public project templates and SOPs. Public, no authentication. | Remote · HTTPLive check: ✓ handshake |
| Kaneme - Your writing identity, measured and portableBuild a voice from your own texts, measure whether a text still sounds like you, then write in it. | Remote · HTTPLive check: ✓ handshake |
| KanonikGovernance runtime for compliance: verified, human-approved writes to a tamper-evident record. | Remote · HTTPLive check: sign-in required |
| Kansei MCP ServerSaaS intelligence for AI agents. 5 unified tools cover 1,000+ services with 91-96% token savings. | Remote & Local · HTTP, stdioLive check: ✓ handshake |