ModelsAtlas
Explore
Atlas / MCP servers / zzaebok / Wikidata

WikidataSAFE

mcp/zzaebok/wikidata
MCP server by zzaebok · Audited 2026-10-08
⚑ Report / re-scanSource ↗

A server implementation for Wikidata API using the Model Context Protocol (MCP).

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
5 4r · 1w · 0d
Transport
—
License
MIT
Stars
49
01

Overview

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

Wikidata MCP Server

[](https://smithery.ai/server/@zzaebok/mcp-wikidata)

A server implementation for Wikidata API using the Model Context Protocol (MCP). This project provides tools to interact with Wikidata, such as searching identifiers (entity and property), extracting metadata (label and description) and executing sparql query.

Installation

Installing via Smithery

To install Wikidata MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @zzaebok/mcp-wikidata --client claude

Installing Manually

Install uv if it is not installed yet.

$ curl -LsSf https://astral.sh/uv/install.sh | sh

Then, install dependencies.

$ git clone https://github.com/zzaebok/mcp-wikidata.git
$ cd mcp-wikidata
$ uv sync
# if you want to run client example together
$ uv sync --extra example

Run

Run the server with:

$ uv run src/server.py

If you want to test it with a simple client code (with langchain-mcp-adapters), run the client with:

# in another shell
$ uv run src/client.py

The LLM extracts valid entity and property identifiers, executes a sparql query, and finally recommend a movie directed by Bong Joon-ho.

See the execution output

{
"messages": [
HumanMessage(
content="Can you recommend me a movie directed by Bong Joonho?",
),
AIMessage(
tool_calls=[
{
"name": "search_entity",
"args": {"query": "Bong Joon-ho"},
}
],
),
ToolMessage(
content="Q495980",
name="search_entity",
),
AIMessage(
tool_calls=[
{
"name": "get_properties",
"args": {"entity_id": "Q49598
Read from source at commit 91bb54ccff3cOBSERVED · 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. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add mcp-wikidata --env OPENAI_API_KEY=${OPENAI_API_KEY} -- uvx mcp-wikidata
claude-desktop
{
  "mcpServers": {
    "mcp-wikidata": {
      "command": "uvx",
      "args": [
        "mcp-wikidata"
      ],
      "env": {
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  }
}
03

Exposed tools (5)

4 read · 1 write · 0 destructive.

ToolRiskDescription
execute_sparqlwrite
get_metadataread
get_propertiesread
search_entityread
search_propertyread
04

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 (2 observation(s))
Network
declared (6 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (2)

MEDIUMFilesystem / path · fs.destructive · CWE-22, CWE-59
Dockerfile:5
RUN apt-get update && apt-get install -y curl && rm -rf /var/lib/apt/lists/*
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.md:24
$ curl -LsSf https://astral.sh/uv/install.sh | sh

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 91bb54ccff3cfull audit observations/trust-audit/mcp-server/zzaebok__wikidata.json · Report an issue / request a re-scan
05

Audit history

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

DateSourceVerdictGradeScoreChange
2026-10-0891bb54ccff3cSAFEB89first audit
06

Questions

What is the Wikidata MCP server?

A server implementation for Wikidata API using the Model Context Protocol (MCP).

What tools does Wikidata expose?

5 in total: 4 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Wikidata 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 Wikidata need?

It reads OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How current is this page?

The grade is for one exact copy of the source (91bb54ccff3c), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement