Chroma (djm81) MCP Server
chroma-mcp-server
PyPI
v0.2.28
Published by djm81 — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Chroma MCP Server - Vector Database Integration for LLM Applications
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 11
high Dynamic code execution in server code (src/chroma_mcp_client/connection.py)MTC-SRC-001
In the server's implementation (`src/chroma_mcp_client/connection.py:115`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: int(f"Getting Embedding Function ('{ef_name}')...", file=sys.stderr) embedding_function: Optional[chromadb.Embedding
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/chroma_mcp_client/connection.py
high Shell/command execution in server code (src/chroma_mcp/dev_scripts/build.py)MTC-SRC-002
In the server's implementation (`src/chroma_mcp/dev_scripts/build.py:18`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: in(cmd)}") result = subprocess.run(cmd, cwd=cwd) return result.returncode def main() -> int: """Main entry
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/chroma_mcp/dev_scripts/build.py
high Shell/command execution in server code (src/chroma_mcp/dev_scripts/publish.py)MTC-SRC-002
In the server's implementation (`src/chroma_mcp/dev_scripts/publish.py:44`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: cmd_str}") result = subprocess.run(cmd, cwd=cwd) return result.returncode def check_dist_files(project_root: P
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/chroma_mcp/dev_scripts/publish.py
high Shell/command execution in server code (src/chroma_mcp/dev_scripts/release.py)MTC-SRC-002
In the server's implementation (`src/chroma_mcp/dev_scripts/release.py:24`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: in(cmd)}") result = subprocess.run(cmd, cwd=cwd) return result.returncode def get_current_version(project_root
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/chroma_mcp/dev_scripts/release.py
high Shell/command execution in server code (src/chroma_mcp_client/analysis.py)MTC-SRC-002
In the server's implementation (`src/chroma_mcp_client/analysis.py:165`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: commits_result = subprocess.run(commits_cmd, capture_output=True, text=True, check=False) if commits_res
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/chroma_mcp_client/analysis.py
high Shell/command execution in server code (src/chroma_mcp_client/indexing.py)MTC-SRC-002
In the server's implementation (`src/chroma_mcp_client/indexing.py:60`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: HEAD"] result = subprocess.run(cmd, capture_output=True, text=True, check=True, encoding="utf-8") return
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/chroma_mcp_client/indexing.py
high Shell/command execution in server code (src/chroma_mcp_client/pytest_plugin.py)MTC-SRC-002
In the server's implementation (`src/chroma_mcp_client/pytest_plugin.py:47`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: t commit_hash = subprocess.check_output(["git", "rev-parse", "HEAD"], cwd=str(project_root)).decode().strip()
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/chroma_mcp_client/pytest_plugin.py
low Shell/command execution in packaging/dev tooling (src/chroma_mcp_client/scripts/analyze_chat.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`src/chroma_mcp_client/scripts/analyze_chat.py:41`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: result = subprocess.run(cli_args, check=False) return result.returncode except Exception as e
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/chroma_mcp_client/scripts/analyze_chat.py
low Shell/command execution in packaging/dev tooling (src/chroma_mcp_client/scripts/log_chat.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`src/chroma_mcp_client/scripts/log_chat.py:40`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: result = subprocess.run(cli_args, check=False) return result.returncode except Exception as e
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/chroma_mcp_client/scripts/log_chat.py
low Shell/command execution in packaging/dev tooling (src/chroma_mcp_client/scripts/log_error.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`src/chroma_mcp_client/scripts/log_error.py:38`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: result = subprocess.run(cli_args, check=False) return result.returncode except Exception as e
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/chroma_mcp_client/scripts/log_error.py
low Shell/command execution in packaging/dev tooling (src/chroma_mcp_client/scripts/log_quality.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`src/chroma_mcp_client/scripts/log_quality.py:41`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: result = subprocess.run(cli_args, check=False) return result.returncode except Exception as e
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/chroma_mcp_client/scripts/log_quality.py
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.2.28 latest |
A 93/100 | 11 | 1.13.0 | 2026-08-25 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan chroma-mcp-server --online --registry pypiOther implementations of Chroma 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More in AI, Memory & Reasoning
FDA device & vehicle recall risk for AI agents: recall history, MAUDE trend, risk score.
Open-source MCP server exposing Agent402.Tools' catalog — 500+ strong: 400+ self-hostable tools + 100 multi-tool skill packs (security-audit, trend-analysis, structured-scrape, decode-blob, forecasting-bake-off) for AI agents — browser, web search & answe
Zero-dependency MCP server that gives AI agents a self-updating project memory in AGENTS.md. Returns merge instructions instead of mutating state, so every change is a reviewable diff.
MCP Apps UI resources and server helpers for n8n
MCP server providing comprehensive access to BookStack knowledge management system
MCP server for tracking achievements with STAR methodology