MaverickMCP — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Track market-data sources and the local-only deployment boundary as the project evolves

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Local stock research, screening, portfolio tracking and backtesting

What we know

Personal stock-analysis MCP using Yahoo Finance data for market data, technical indicators, screening, portfolio tracking and optional research/backtesting.

Maintenance / activity evidence

Observed Oct 4, 2026 (UTC)Fix MCP tool validation and add process end-to-end testing ( 311)

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Activity source · commits ↗Activity source · releases ↗

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Read/research and local portfolio-tracking scope.
No auth for local core server; provider key for optional research.
Sensitive access: Portfolio holdings/preferences, LLM provider key

This is analysis/backtesting, not brokerage execution; the main external risks are data and optional model providers.

Security source · repository notice ↗Security source · policy file ↗

Full authority, access and evidence limits are available in Review context and Access & risk.

Popularity

677 repository stars

Stars observed Sep 25, 2026.

Preserve any already-reviewed adoption metrics in MCP100. Batch 4 did not refresh package downloads because the package-stats provider had insufficient credits.

All limitations / Review context

Does the server remain local-first and what market-data tools are current?

The README documents a local, personal-use MCP server that binds to loopback by default and intentionally has no authentication; the assessment is limited to public tracking and records the deployment-scope limitation.

This is analysis/backtesting, not brokerage execution; the main external risks are data and optional model providers.
Read/research and local portfolio-tracking scope.
No auth for local core server; provider key for optional research.
Market data comes from external sources; optional research may send context to an LLM provider.
Sensitive access: Portfolio holdings/preferences, LLM provider key
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
The project is intended for local personal use and lacks authentication by design; no external deployment or authorization review was performed.
No independent runtime, installation, or comprehensive security audit was performed.
No installation, runtime, client matrix, or complete tool-contract audit was performed in this review.
Exact canonical package/install command
Core tools analyze data but do not execute trades.
Optional research requires an LLM key.

Original activity observations

2026-10-04T23:48:03Z: Fix MCP tool validation and add process end-to-end testing ( 311)

Technical identity

github.com/wshobson/maverick-mcp

Exact implementation source: https://github.com/wshobson/maverick-mcp ↗
Reviewed resource type: MCP Server
Repository identity: wshobson/maverick-mcp

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 6, 2026

GitHub repository ↗
wshobson/maverick-mcp
Recorded repository material and project history.

Setup · Watchlist

Install & Agents

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Install / connect
Publisher instructions
Publisher warns that pre-existing PyPI package differs or predates correctness fixes. Install from current GitHub checkout with Python ≥3.12 + uv; do not `pip install` similarly named old release by default.
publisher setup entry · Publisher instructions
git clone https://github.com/wshobson/maverick-mcp.git cd maverick-mcp uv sync cp .env.example .env
Configure / authenticate
MCP100 setup guide
Configure read-only data provider settings; register stdio from local checkout or run make dev for http://localhost:8003/mcp (NO trailing slash).
Check connection
Suggested check
List tools or ask for a non-trading market summary; do not trade.
Remove / uninstall / revoke
MCP100 setup guide
Remove the `maverick` MCP registration from its chosen host, and stop any running checkout-based MCP process. This project warns against installing a lookalike/unmaintained PyPI name; do not run `pip uninstall` blindly against an unrelated package. Client remove command is an MCP100 composed example: replace the registration name with your actual installed name.
Client unregistration, program uninstall, persistent-data deletion, and credential revocation must be treated separately.
Remove client registration · Claude Code only · MCP100 composed guide
claude mcp remove maverick

Official Documentation & Sources

What it does

Personal stock-analysis MCP using Yahoo Finance data for market data, technical indicators, screening, portfolio tracking and optional research/backtesting.

Capability: Finance & Payments
Resource type: MCP Server
Industry: Financial Services & Investing
Best fit: Local stock research, screening, portfolio tracking and backtesting

Representative uses

Get market data
Compute technical indicators
Screen stocks
Track a portfolio
Run optional backtests/research

Limitations

Core tools analyze data but do not execute trades.
Optional research requires an LLM key.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: No auth for local core server; provider key for optional research.
Permissions: Read/research and local portfolio-tracking scope.
Data handling: Market data comes from external sources; optional research may send context to an LLM provider.
Cost: usage_based
Risk and cautions: This is analysis/backtesting, not brokerage execution; the main external risks are data and optional model providers.

Access scope and cautions

Write actions: None in the reviewed inventory
Sensitive access: Portfolio holdings/preferences LLM provider key
Risk level: moderate

FAQ

Based on reviewed evidence as of 2026-10-06. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Get market data; Compute technical indicators; Screen stocks; Track a portfolio; Run optional backtests/research.

What authentication is documented?

Core tools require no API key; optional research uses model-provider key.

Can it modify data or perform write operations?

The reviewed inventory lists no write actions. An empty inventory alone does not establish read-only authority. Recorded permission boundary: Read/research and local portfolio-tracking scope.

What data-handling boundary should I consider?

Market data comes from external sources; optional research may send context to an LLM provider. Recorded sensitive-access context: Portfolio holdings/preferences; LLM provider key.

What limitations and risks should I check before use?

This is analysis/backtesting, not brokerage execution; the main external risks are data and optional model providers. Core tools analyze data but do not execute trades. Optional research requires an LLM key. The project is intended for local personal use and lacks authentication by design; no external deployment or authorization review was performed. No independent runtime, installation, or comprehensive security audit was performed.

What cost model is recorded?

The reviewed cost model is usage based. This classification does not establish current prices, quotas or the cost of every downstream operation. Check the applicable service terms before authorizing paid actions.

Is this an official MCP?

Seth Hobson is listed as Community implementation in MCP100’s current evidence.