Directory / alpacahq/alpaca-mcp-server
alpacahq/alpaca-mcp-server
Alpaca’s official MCP Server lets you trade stocks, ETFs, crypto, and options, run data analysis, and build strategies in plain English directly from your favorite LLM tools and IDEs
cdb0e46, rubric v1.1. Reviewer summary: Official Alpaca MCP server. Defaults to paper (ALPACA_PAPER_TRADE=true) and can restrict exposed tools with ALPACA_TOOLSETS. It has no order size or loss limits of its own.
Facts
| Repository | https://github.com/alpacahq/alpaca-mcp-server |
|---|---|
| Type | MCP server |
| Strategies | Not tagged |
| Brokers | Alpaca |
| License | MIT |
| Language | Python |
| Last commit | 2026-10-23 (1 days before the scan) |
| Last scanned | 2026-10-24 |
| Stars | 1040 (shown for context, never scored) |
Score breakdown
| Factor | Points | How it was decided |
|---|---|---|
| Risk limits and kill switch | 5 / 20 | No size or loss limits. The scanner's stop-loss hit is a bracket order parameter. ALPACA_TOOLSETS can restrict which tools an assistant sees, which I count as a partial gate (5). Reviewer confirmed the scanner result. Scanner evidence (1, automated, can include false matches)
|
| License | 15 / 15 | MIT (OSI approved) Reviewer confirmed the scanner result. Scanner evidence (1, automated, can include false matches)
|
| Last commit on default branch | 15 / 15 | 1 days since last commit Fact from the commit date, no judgment involved. Scanner evidence (1, automated, can include false matches)
|
| Tests | 15 / 15 | 101 test cases found in 11 test files; CI test step found Reviewer confirmed the scanner result. Scanner evidence (4, automated, can include false matches)
|
| Paper or dry-run mode | 15 / 15 | ALPACA_PAPER_TRADE defaults to true and the README says to use a paper account. Reviewer confirmed the scanner result. Scanner evidence (3, automated, can include false matches)
|
| README quality | 10 / 10 | install steps, config or env vars, explains what it does, risk disclaimer, 29658 chars Reviewer confirmed the scanner result. Scanner evidence (2, automated, can include false matches)
|
| Broker detection | 10 / 10 | Alpaca (deps, code, readme) Reviewer confirmed the scanner result. Scanner evidence (1, automated, can include false matches)
|
| Total | 85 / 100 | Grades: A 85+, B 70+, C 55+, D 40+, F below. |
Grades measure public repo hygiene on the scan date. They say nothing about profits, safety or security. We did not run this code. Full rubric and patterns.
Something wrong?
Report a correction Request removal (maintainers)
Corrections and removals are public GitHub issues. We reply within 7 days and every change is in the repo history. Sponsors get no special treatment: see our policy.
Badge for your README
Once the site has a public address, shields.io can read /badge/alpacahq--alpaca-mcp-server.json from it. Badges show the grade and whether it was reviewed. Maintainers may use one without asking.