Timefire MCP server
Commit Nov 13, 2026Access a public record of graded AI stock forecasts to review track records and verify forecast seals.
Also known as timefire-ai/timefire-plugin, record
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.1.1
- Last commit
- Nov 13, 2026
- License
- MIT
What is Timefire MCP?
Timefire accesses a public record of graded AI stock forecasts to review track records and verify forecast seals.
Summary generated from the project's README
About Timefire MCP server
Reviewing the historical accuracy of AI-generated stock predictions is what Timefire enables for investors and researchers. By connecting an AI assistant to a public record of graded forecasts, users can examine how previous predictions performed after a ten-day grading period. This read-only connection allows you to inspect specific books of forecasts, check hit rates, and verify the authenticity of forecast seals without needing to create an account.
Users interact with the server through plain language requests, which the assistant translates into tool calls. The server functions by sending inputs like tickers, dates, or search terms to a hosted remote API. It provides access to twelve distinct tools that return data on graded books, such as portfolio values compared to RSP or specific stock inclusions like Apple. Because the plugin runs entirely on a remote server, no local processing is required on your machine.
What you can do with it
- 1Verify forecast authenticityYou can ask your assistant to check the most recent graded book to confirm its timestamp and validity.
- 2Analyze historical accuracyA developer can request the overall hit rate across all previously graded books to assess performance.
- 3Filter forecasts by tickerYou can retrieve every graded book that contained a specific stock like Apple.
- 4Compare portfolio performanceRequest a comparison between the equal-weighted portfolio value and the RSP index.
Written from the project's README. Every use case is checked against a quote from it.
How to install Timefire MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Timefire MCP in Claude Code
$ claude mcp add --transport http record https://api.timefire.ai/mcp/Install Timefire MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"record": {
"url": "https://api.timefire.ai/mcp/"
}
}
}Install Timefire MCP in VS Code
.vscode/mcp.json
{
"servers": {
"record": {
"type": "http",
"url": "https://api.timefire.ai/mcp/"
}
}
}Install Timefire MCP in VS Code CLI
$ code --add-mcp '{"name":"record","type":"http","url":"https://api.timefire.ai/mcp/"}'Install Timefire MCP in Codex
$ codex mcp add record --url https://api.timefire.ai/mcp/Install Timefire MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.record] url = "https://api.timefire.ai/mcp/"
Install Timefire MCP in Gemini CLI
$ gemini mcp add -s user --transport http record https://api.timefire.ai/mcp/Install Timefire MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"record": {
"url": "https://api.timefire.ai/mcp/",
"type": "http"
}
}
}Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachabletimefire-ai/timefire-plugin is public and reachablegithub.com/timefire-ai/timefire-plugin ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/timefire-ai/timefire-plugin ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 593 msPass
README
View on GitHubTimefire
Check the public record of Timefire's AI stock forecasts from your assistant.
Timefire seals each book of forecasts before outcomes are known, then grades it ten trading days later. This plugin connects your assistant to that record, so you can look up graded books, review the track record, and verify a book's seal yourself.
It's read-only and needs no account. This is not investment advice.
Use it
Ask in plain words, and your assistant picks the tool:
- "Verify the newest graded book and tell me what the timestamp proves."
- "What is the hit rate across every graded book?"
- "Show me every graded book that included Apple."
- "Show me the equal-weighted portfolio value against RSP."
What's inside
The plugin holds one thing: a connection to Timefire's hosted server at https://api.timefire.ai/mcp/. It has 12 read-only tools, listed at timefire.ai/developers/tools. To connect without the plugin, see client setup.
Data
The plugin runs nothing on your machine. When your assistant uses a tool, it sends that tool's inputs, such as a date, a ticker or search words, to api.timefire.ai. Graded books come back, never sealed ones. See the privacy policy.
Support
Email hello@timefire.ai.
Timefire MCP questions
How do I add Timefire MCP to Claude Code?
Run claude mcp add --transport http record https://api.timefire.ai/mcp/ in your terminal. Add --scope user to make it available in every project.
How do I add Timefire MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How do I access the Timefire data?
You can access the data by asking your assistant in plain words, such as asking for hit rates or specific stock performance.
Does using this server require an account?
No, the server is read-only and does not require an account to use.
What kind of data is returned by the tools?
The tools return graded books, but they never return books that are still sealed.