Atlas / MCP servers / kkjdaniel / BGG

BGGSAFE

mcp/kkjdaniel/bgg

BGG MCP provides access to BoardGameGeek and a variety of board game related data through the Model Context Protocol. Enabling retrieval and filtering of board game data, user collections, and profiles.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
—
Transport
stdio · streamable-http
License
MIT
Stars
53
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

An MCP server that gives AI assistants access to BoardGameGeek: game details, collections, prices, recommendations and rules answers.

[](https://archestra.ai/mcp-catalog/kkjdaniel__bgg-mcp) [](https://github.com/modelcontextprotocol/registry) [](https://go.dev/) [](LICENSE.md) [](https://modelcontextprotocol.io)

BGG MCP provides access to the BoardGameGeek API through the Model Context Protocol, enabling retrieval and filtering of board game data, user collections, and profiles. The server is implemented in Go, using the GoGeek library, which helps ensure robust API interactions.

Price data is provided by BoardGamePrices.co.uk, offering real-time pricing from multiple retailers.

Game recommendations are powered by Recommend.Games, which provides algorithmic similarity recommendations based on BoardGameGeek data.

Demo

[](https://youtu.be/cNX4WwVbFko)

[▶️ Watch the Rules Tool Demo Video](https://youtu.be/cNX4WwVbFko)

Tools

Read from source at commit a2035ec5db96OBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code (oci)
claude mcp add bgg-mcp:1.7.0 -- docker run -i --rm docker.io/kdaniel/bgg-mcp:1.7.0:None
03

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeWARN
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
UNDECLARED (1 observation(s))
Network
declared (5 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (2)

MEDIUMFilesystem / path · fs.system_paths · CWE-22, CWE-59
Dockerfile:26
ENTRYPOINT ["/usr/local/bin/bgg-mcp"]
LOWInventory / provenance · mcp.no_tools_extracted · CWE-1104
server.json
Why it matters. the tool list is enumerated at runtime by tools/list, not declared in source
Fix. the page says so rather than showing an empty table

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha a2035ec5db96full audit observations/trust-audit/mcp-server/kkjdaniel__bgg.json · Report an issue / request a re-scan
04

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-08a2035ec5db96SAFEB89first audit
05

Questions

What is the BGG MCP server?

BGG MCP provides access to BoardGameGeek and a variety of board game related data through the Model Context Protocol. Enabling retrieval and filtering of board game data, user collections, and profiles.

Is BGG safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does BGG need?

No credential environment variables were found in its source, so it appears to need none.

How does BGG run?

It speaks stdio and streamable-http, so it runs as a local process your client starts.

How current is this page?

The grade is for one exact copy of the source (a2035ec5db96), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement