Alpaca MCP Server connects AI assistants and coding tools to Alpaca’s trading API, allowing them to perform natural-language operations involving stocks, options, crypto, portfolios, and market data. Traders and developers use it to analyze data and manage trading activities through compatible LLM tools and IDEs.
Borrowing it
Nothing to install: this file belongs to alpacahq/alpaca-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alpacahq/alpaca-mcp-server/main/AGENTS.mdgit clone --depth 1 https://github.com/alpacahq/alpaca-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/alpacahq/alpaca-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/alpacahq/alpaca-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/alpacahq/alpaca-mcp-server/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/alpacahq/alpaca-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/alpacahq/alpaca-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02127 | $0.02127 |
| Opus 5.5 | $0.00851 | $0.00851 |
| Sonnet 5.5 | $0.00425 | $0.00425 |
| Haiku 4.5 | $0.00213 | $0.00213 |
Grade A, and why
alpaca-mcp-server AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
2 near-identical copies found in the catalogue:
- alpaca-mcp-server-RFJq AGENTS.md — 100% identical, 51 lines differ
- alpacahq_alpaca-mcp-server AGENTS.md — 86% identical, 57 lines differ
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Architecture Overview
This MCP server auto-generates tools from bundled OpenAPI specs (src/alpaca_mcp_server/specs/) using FastMCP's from_openapi(). Tool names, descriptions, and output risk classifications are defined in tool_registry.py. Complex endpoints (orders, historical data) use hand-written overrides in overrides.py and market_data_overrides.py. Toolset filtering is defined in toolsets.py. A trust-boundary middleware (security.py) wraps every tool result in a security envelope to mitigate prompt injection via tool outputs.
The test suite has three layers:
tests/test_integrity.py— Spec ↔ toolset ↔ names consistency, plus release version alignment (no network)tests/test_server_construction.py— Server builds correctly and exposes the expected tool set (no network)tests/test_paper_integration.py— Real API calls against Alpaca paper (needs credentials)
CI is defined in .github/workflows/ci.yml with two jobs: test-core (runs on every PR) and test-integration (runs when ALPACA_API_KEY / ALPACA_SECRET_KEY secrets are available). PyPI publishing is defined in .github/workflows/publish-pypi.yml and runs only when a GitHub Release is published.
Syncing OpenAPI Specs
When asked to "sync the MCP server" or "update specs", follow this process:
Step 1: Download latest specs
Run the sync script:
./scripts/sync-specs.sh
After downloading, the script rewrites the declared OpenAPI version from 3.1.2 to 3.1.1. FastMCP parses specs with openapi-pydantic, which only accepts 3.1.0 and 3.1.1 and rejects anything newer, so without this the server builds zero tools. Expect a one-character difference from the published spec. Remove that line once openapi-pydantic supports 3.1.2.
Step 2: Diff the specs
Check what changed:
git diff src/alpaca_mcp_server/specs/
Classify every change into one of three categories:
A. Modified existing endpoints
Parameter or schema changes to endpoints already in the allowlist (toolsets.py).
Action for auto-generated tools: No code changes needed — the spec update is sufficient.
Action for overrides: If the modified endpoint has its operationId in OVERRIDE_OPERATION_IDS (e.g., postOrder), the auto-generator is bypassed and the hand-written override in overrides.py or market_data_overrides.py is used instead. Spec changes do NOT flow through to overrides automatically. For every override whose underlying spec changed, you must:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +45 lines · +502 tokens per session 87ab0bb1ac86
- 1mo ago First seen · 121 lines · 1,625 tokens per session scan A 3f2917fc7ab4
alpaca-mcp-server AGENTS.md is an instructions file published in the GitHub repository alpacahq/alpaca-mcp-server (1,049 stars, last pushed yesterday), licensed MIT. It adds 2,127 tokens to every session, about $0.0085 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.