Official Alpaca MCP server for Trading API workflows, including account and portfolio data, orders, positions, watchlists, assets, stocks, crypto, options, news, corporate actions, and market data.
Alpaca MCP Server can expose account balances, buying power, positions, orders, activities, watchlists, assets, market data, news, corporate actions, stocks, crypto, options data, and trading tools to the MCP client., Trading tools can place stock, ETF, crypto, and option orders, cancel orders, close positions, liquidate portfolios, replace orders, and exercise or mark do-not-exercise option contracts., Paper trading is the default documented mode; setting `ALPACA_PAPER_TRADE=false` points trading calls at live Alpaca accounts and can result in real financial losses., Require explicit human approval before any order placement, cancellation, liquidation, option exercise, live-account change, or strategy involving leverage, margin, extended hours, crypto, or options., Use `ALPACA_TOOLSETS` to restrict the server to read-only or data-only toolsets when trading tools are not needed., The upstream order override code warns that read timeouts may happen after an order was sent; users should check open orders before retrying to avoid duplicate trades.
Privacy notes
Alpaca API keys, secret keys, account IDs, balances, buying power, portfolio history, activities, positions, orders, watchlists, option contracts, crypto holdings, and trade history can be exposed to the MCP client., Prompts and responses may include private trading strategy, portfolio allocation, order intent, symbols, quantities, prices, client order IDs, and market data queries., MCP clients, model providers, terminal history, logs, and chat transcripts may retain financial data and trading instructions., Upstream documentation states the server sends an Alpaca MCP user agent string for API calls; review Alpaca privacy and disclosure materials for account data handling.
Author
Alpaca
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
6 safety and 4 privacy notes across 4 risk areas. Review closely: credentials & tokens, network access, third-party handling.
4 areas
SafetyGeneralAlpaca MCP Server can expose account balances, buying power, positions, orders, activities, watchlists, assets, market data, news, corporate actions, stocks, crypto, options data, and trading tools to the MCP client.
SafetyGeneralTrading tools can place stock, ETF, crypto, and option orders, cancel orders, close positions, liquidate portfolios, replace orders, and exercise or mark do-not-exercise option contracts.
SafetyGeneralPaper trading is the default documented mode; setting `ALPACA_PAPER_TRADE=false` points trading calls at live Alpaca accounts and can result in real financial losses.
SafetyGeneralRequire explicit human approval before any order placement, cancellation, liquidation, option exercise, live-account change, or strategy involving leverage, margin, extended hours, crypto, or options.
SafetyGeneralUse `ALPACA_TOOLSETS` to restrict the server to read-only or data-only toolsets when trading tools are not needed.
SafetyGeneralThe upstream order override code warns that read timeouts may happen after an order was sent; users should check open orders before retrying to avoid duplicate trades.
PrivacyCredentials & tokensAlpaca API keys, secret keys, account IDs, balances, buying power, portfolio history, activities, positions, orders, watchlists, option contracts, crypto holdings, and trade history can be exposed to the MCP client.
PrivacyGeneralPrompts and responses may include private trading strategy, portfolio allocation, order intent, symbols, quantities, prices, client order IDs, and market data queries.
PrivacyThird-party handlingMCP clients, model providers, terminal history, logs, and chat transcripts may retain financial data and trading instructions.
PrivacyNetwork accessUpstream documentation states the server sends an Alpaca MCP user agent string for API calls; review Alpaca privacy and disclosure materials for account data handling.
Disclosure: Official Alpaca MCP server published as the `alpaca-mcp-server` PyPI package under an MIT license. Trading and market-data use is subject to Alpaca account, brokerage, crypto, options, and data-plan terms.
Safety notes
Alpaca MCP Server can expose account balances, buying power, positions, orders, activities, watchlists, assets, market data, news, corporate actions, stocks, crypto, options data, and trading tools to the MCP client.
Trading tools can place stock, ETF, crypto, and option orders, cancel orders, close positions, liquidate portfolios, replace orders, and exercise or mark do-not-exercise option contracts.
Paper trading is the default documented mode; setting `ALPACA_PAPER_TRADE=false` points trading calls at live Alpaca accounts and can result in real financial losses.
Require explicit human approval before any order placement, cancellation, liquidation, option exercise, live-account change, or strategy involving leverage, margin, extended hours, crypto, or options.
Use `ALPACA_TOOLSETS` to restrict the server to read-only or data-only toolsets when trading tools are not needed.
The upstream order override code warns that read timeouts may happen after an order was sent; users should check open orders before retrying to avoid duplicate trades.
Privacy notes
Alpaca API keys, secret keys, account IDs, balances, buying power, portfolio history, activities, positions, orders, watchlists, option contracts, crypto holdings, and trade history can be exposed to the MCP client.
Prompts and responses may include private trading strategy, portfolio allocation, order intent, symbols, quantities, prices, client order IDs, and market data queries.
MCP clients, model providers, terminal history, logs, and chat transcripts may retain financial data and trading instructions.
Upstream documentation states the server sends an Alpaca MCP user agent string for API calls; review Alpaca privacy and disclosure materials for account data handling.
Prerequisites
Python 3.10 or newer and uv or uvx available.
Alpaca API key and secret key for a paper trading account or an explicitly approved live account.
Review of Alpaca account permissions, paper versus live mode, options approval, crypto availability, and market data subscription limits.
A narrow `ALPACA_TOOLSETS` allowlist for the workflow whenever full trading access is not required.
Human review procedures for any order placement, cancellation, position closing, option exercise, or live account action.
Schema details
Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
15 minutes
Difficulty
advanced
Tool listing metadata
Disclosure
Official Alpaca MCP server published as the `alpaca-mcp-server` PyPI package under an MIT license. Trading and market-data use is subject to Alpaca account, brokerage, crypto, options, and data-plan terms.
Alpaca MCP Server is Alpaca's official MCP server for the Alpaca Trading API. It
uses FastMCP and Alpaca OpenAPI specs to expose account, trading, portfolio,
asset, market data, watchlist, news, corporate action, stock, crypto, and
options workflows to MCP clients.
Use it for supervised paper-trading, account analysis, portfolio review, market
data retrieval, and carefully gated trading workflows. Treat live-trading mode
as a financial operations capability that requires human approval and explicit
risk controls.
These sources were reviewed on 2026-06-06. Prefer the live repository,
README, PyPI metadata, license, package manifest, MCP registry metadata, CLI
entrypoint, FastMCP server builder, toolset definitions, and order override
implementation for current setup and behavior details.
Features
Run as a stdio MCP server with uvx alpaca-mcp-server.
Configure paper or live trading with ALPACA_PAPER_TRADE.
Restrict exposed capabilities with ALPACA_TOOLSETS.
Read account information, account configuration, portfolio history, and
account activities.
Retrieve and manage orders, positions, watchlists, assets, market calendar,
market clock, corporate actions, and news.
Place stock, ETF, crypto, and options orders through curated order tools.
Retrieve stock, crypto, options, fixed income, and index market data depending
on enabled toolsets and account/data access.
Use OpenAPI-derived tools plus hand-crafted overrides for complex order and
market-data endpoints.
Installation
Configure the MCP client with Alpaca credentials. Keep paper trading enabled
unless a live-trading workflow is explicitly approved:
claude mcp add alpaca --scope user --transport stdio uvx alpaca-mcp-server --env ALPACA_API_KEY=YOUR_ALPACA_API_KEY --env ALPACA_SECRET_KEY=YOUR_ALPACA_SECRET_KEY
Set ALPACA_TOOLSETS to the smallest set needed. For data-only use, omit the
trading toolset.
Use Cases
Ask Claude to summarize paper account balances and buying power.
Retrieve current positions and open orders for review.
Pull recent stock, crypto, or options market data.
Check market calendar, market clock, news, and corporate actions.
Manage watchlists for research workflows.
Test paper-trading order flows under human supervision.
Restrict Claude to market-data toolsets for analysis-only sessions.
Safety and Privacy
Alpaca MCP Server can place real trades when configured for live trading. Keep
paper mode enabled for experiments, use data-only toolsets whenever possible,
and require human confirmation for every trading, cancellation, liquidation, or
option-exercise action.
Options, crypto, margin, extended-hours, bracket, stop, trailing-stop, and
multi-leg strategies carry significant financial risk. Claude-generated orders
are not investment advice and can be wrong, stale, incomplete, or unsuitable for
the account.
Alpaca credentials and account data are highly sensitive. Do not paste real API
keys into prompts or shared logs. Treat MCP transcripts as financial records
when they contain balances, positions, orders, symbols, quantities, prices,
portfolio history, activities, or strategy details.
Duplicate Check
Existing entries cover financial research and market data tools such as Drillr
and TradingView, but no Alpaca MCP Server, alpacahq/alpaca-mcp-server,
alpaca-mcp-server PyPI package, or Alpaca Trading API MCP entry was found in
content/mcp.
Show that Alpaca MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/alpaca-mcp-server)
How it compares
Alpaca MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
Official Alpaca MCP server for Trading API workflows, including account and portfolio data, orders, positions, watchlists, assets, stocks, crypto, options, news, corporate actions, and market data.
Apache-licensed TypeScript MCP server for Obsidian vaults with stdio and Streamable HTTP transports, Local REST API access, note search, section-aware edits, tag/frontmatter management, path policies, and read-only controls.
MCP support in Azure Data API Builder for exposing configured database entities as MCP tools, including entity discovery and DML operations over Azure databases and supported on-premises data stores.
✓Alpaca MCP Server can expose account balances, buying power, positions, orders, activities, watchlists, assets, market data, news, corporate actions, stocks, crypto, options data, and trading tools to the MCP client.
Trading tools can place stock, ETF, crypto, and option orders, cancel orders, close positions, liquidate portfolios, replace orders, and exercise or mark do-not-exercise option contracts.
Paper trading is the default documented mode; setting `ALPACA_PAPER_TRADE=false` points trading calls at live Alpaca accounts and can result in real financial losses.
Require explicit human approval before any order placement, cancellation, liquidation, option exercise, live-account change, or strategy involving leverage, margin, extended hours, crypto, or options.
Use `ALPACA_TOOLSETS` to restrict the server to read-only or data-only toolsets when trading tools are not needed.
The upstream order override code warns that read timeouts may happen after an order was sent; users should check open orders before retrying to avoid duplicate trades.
✓Cyanheads Obsidian MCP can read, list, search, create, append, patch, replace, delete, tag, and edit frontmatter in the configured vault through the Local REST API plugin.
The server defaults to full-vault access unless read paths, write paths, or read-only mode are configured.
Set `OBSIDIAN_READ_ONLY=true` for research-only workflows, then narrow writes with `OBSIDIAN_WRITE_PATHS` before allowing note edits.
Delete operations are permanent in the vault and should require human review even when the MCP host supports destructive-tool prompts.
Command-palette tools are disabled unless `OBSIDIAN_ENABLE_COMMANDS=true`; command execution can trigger opaque or destructive Obsidian plugin behavior.
Streamable HTTP deployments should use JWT or OAuth auth before being exposed beyond a trusted local machine.
✓Data API Builder MCP tools can expose database entity metadata and perform DML operations depending on DAB configuration and permissions.
Built-in tools include entity discovery and record read, create, update, delete, aggregate, and execute-style workflows in the MCP source tree.
The upstream README still labels endpoint support as coming soon while source, samples, and testing docs expose MCP behavior; verify the exact release before production use.
Use least-privilege roles, disable DML tools where not required, and require approval before write, delete, execute, or stored-procedure operations.
Do not connect MCP clients to production databases without backups, audit logging, query limits, and rollback procedures.
✓This server retrieves financial market data; do not treat tool output or model summaries as investment, trading, tax, or legal advice.
Current prices, crypto prices, filings, and news can be delayed, incomplete, rate limited, or unavailable depending on API plan and market conditions.
Review generated analysis before using it in portfolio decisions, trading workflows, client reports, or compliance-sensitive research.
The server sends ticker symbols, date ranges, filing filters, and research queries to the Financial Datasets API.
Privacy notes
✓Alpaca API keys, secret keys, account IDs, balances, buying power, portfolio history, activities, positions, orders, watchlists, option contracts, crypto holdings, and trade history can be exposed to the MCP client.
Prompts and responses may include private trading strategy, portfolio allocation, order intent, symbols, quantities, prices, client order IDs, and market data queries.
MCP clients, model providers, terminal history, logs, and chat transcripts may retain financial data and trading instructions.
Upstream documentation states the server sends an Alpaca MCP user agent string for API calls; review Alpaca privacy and disclosure materials for account data handling.
✓Vault notes, headings, block references, frontmatter, tags, file metadata, outgoing links, search queries, command names, plugin status, and edit history may be exposed to the MCP client and model provider.
API keys, local plugin endpoints, HTTP auth settings, path allowlists, logs, OpenTelemetry traces, and Docker environment variables can reveal private vault structure or credentials.
Tag listing is vault-wide in upstream behavior and can reveal tag names outside narrowed read paths.
Notes may contain personal journals, client work, credentials, meeting notes, research plans, health data, or other sensitive knowledge-base content.
✓Entity metadata can expose database names, table names, view names, stored procedure names, field names, key fields, relationships, permissions, and role design.
Read and DML tool calls can expose or change customer records, internal data, regulated fields, identifiers, audit fields, and business workflow state.
Connection strings, role headers, MCP URLs, logs, request bodies, result payloads, and MCP transcripts can contain sensitive operational or personal data.
Redact database values, connection details, entity names, role names, and query results before sharing prompts, screenshots, logs, or generated notes.
✓API keys must be stored in environment variables or local secret managers and never committed to configuration files.
Queried tickers, crypto symbols, time ranges, filings, and news requests can reveal research interests, watchlists, client assignments, or trading hypotheses.
Tool outputs may include financial statements, prices, filings, and news that become part of the model context and logs.
Avoid sending private portfolio holdings, customer identifiers, or material non-public information through prompts or tool arguments.
Prerequisites
Python 3.10 or newer and uv or uvx available.
Alpaca API key and secret key for a paper trading account or an explicitly approved live account.
Review of Alpaca account permissions, paper versus live mode, options approval, crypto availability, and market data subscription limits.
A narrow `ALPACA_TOOLSETS` allowlist for the workflow whenever full trading access is not required.
Node.js 24 or newer, or Bun 1.3.11 or newer.
Obsidian vault with the Obsidian Local REST API community plugin enabled.
Local REST API key stored in the MCP client environment.
Stdio MCP client, or reviewed Streamable HTTP deployment with authentication.
Reviewed Azure Data API Builder configuration with the MCP runtime section enabled.
Supported Azure or on-premises database connection configured through DAB.
DAB entity permissions, role headers, DML tool flags, and per-entity MCP settings reviewed before exposing tools.
MCP client support for the transport used by the deployed DAB server.
Python 3.11 or newer, matching the upstream project metadata.
uv installed on the machine running the MCP server.
A cloned checkout of `financial-datasets/mcp-server`.
Financial Datasets API key stored as `FINANCIAL_DATASETS_API_KEY`.
Install
uvx alpaca-mcp-server
npx -y obsidian-mcp-server@latest
Enable the DAB runtime MCP section, start Data API Builder with the reviewed configuration, and connect an MCP client to the configured MCP path.
uv run server.py
Config
Manual-only setup:
claude mcp add alpaca --scope user --transport stdio uvx alpaca-mcp-server --env ALPACA_API_KEY=YOUR_ALPACA_API_KEY --env ALPACA_SECRET_KEY=YOUR_ALPACA_SECRET_KEY