MCP server giving LLM agents access to databases, files, graphs, and a full data science toolkit — 52 tools across 13 database types and 20+ file formats
- capability exposure inferred + 14
- recent drift inferred + 20
- tool safety inferred + 12
- trust mitigators mixed − 5
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 9m ago · see ecosystem CVEs →
- B · 33 → C · 41
No known CVEs for this server.
- high dangerous code
dynamic exec: eval()/exec(), __import__(), pickle.loads()
analyzed commit b0fae0b · analyzer v28 · 1d ago
skills & prompt files 18
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/exploration/data-quality/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/exploration/explore-data/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/exploration/find-reference-data/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/graph-data/graph-data-explore/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/modeling/anomaly-detection/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/modeling/cluster-analysis/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/modeling/dimensionality-reduction/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/modeling/forecast/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/modeling/geospatial/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/modeling/optimization/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/modeling/regression/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/statistical/ab-test/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/statistical/analyze-correlations/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/statistical/hypothesis-test/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/statistical/sampling-estimation/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/workflow/data-pipeline/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/workflow/process-control/SKILL.md
- skill ChrisGVE-localdata-mcp-b0fae0b/skills/workflow/research-pipeline/SKILL.md
danger signals5
- dynamic code execution eval()/exec() ChrisGVE-localdata-mcp-b0fae0b/src/localdata_mcp/domains/optimization/_tool_functions_lp.py :176
return eval(objective_function, {"__builtins__": {}}, local_vars) - dynamic code execution __import__() ChrisGVE-localdata-mcp-b0fae0b/src/localdata_mcp/pipeline/adapters.py :645
__import__(library_name) - dynamic code execution pickle.loads() ChrisGVE-localdata-mcp-b0fae0b/src/localdata_mcp/pipeline/integration/performance_optimization/_cache.py :434
return pickle.loads(decompressed) - dynamic code execution __import__() ChrisGVE-localdata-mcp-b0fae0b/src/localdata_mcp/server/database_manager.py :4206
mod = __import__(lib_name) - dynamic code execution eval()/exec() ChrisGVE-localdata-mcp-b0fae0b/tests/test_backward_compatibility_integration.py :26
exec(
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:ChrisGVE/localdata-mcp/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of ChrisGVE.