Arize Phoenix MCP Server
arize-phoenix
PyPI
v20.8.0
Published by arize-ai — 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.
AI Observability and Evaluation
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 4
high Reads a sensitive credential path or dumps the environment (src/phoenix/config.py)MTC-SRC-006
In the server's implementation (`src/phoenix/config.py:236`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ured (via environment, ~/.aws/credentials, or IAM role) - AWS region configured via standard AWS methods - The database
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/phoenix/config.py
high Reads a sensitive credential path or dumps the environment (src/phoenix/db/types/model_provider.py)MTC-SRC-006
In the server's implementation (`src/phoenix/db/types/model_provider.py:198`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: n (IAM role, env vars, ~/.aws/credentials) For Azure: DefaultAzureCredential (Managed Identity, Azure CLI, env vars)
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/phoenix/db/types/model_provider.py
high Dynamic code execution in server code (src/phoenix/server/api/helpers/experiment_run_filters.py)MTC-SRC-001
In the server's implementation (`src/phoenix/server/api/helpers/experiment_run_filters.py:470`): 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: e an attribute for your eval (label, score, etc.)" ) @dataclass(frozen=True) class ExperimentRunEvalAttribute(
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/phoenix/server/api/helpers/experiment_run_filters.py
high Shell/command execution in server code (evals/pxi/harness/run_experiment.py)MTC-SRC-002
In the server's implementation (`evals/pxi/harness/run_experiment.py:125`): 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: return subprocess.check_output(["git", *args], text=True).strip() except (OSError, subprocess.Calle
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 evals/pxi/harness/run_experiment.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 10
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 |
|---|---|---|---|---|
v20.8.0 latest |
A 93/100 | 4 | 1.13.0 | 2026-09-05 |
v20.7.0 |
A 93/100 | 4 | 1.13.0 | 2026-09-04 |
v20.4.0 |
A 93/100 | 4 | 1.13.0 | 2026-08-27 |
v20.3.0 |
A 93/100 | 3 | 1.13.0 | 2026-08-25 |
v20.2.1 |
A 93/100 | 3 | 1.12.1 | 2026-08-15 |
Show 5 more versions ↓
v20.2.0 |
A 93/100 | 3 | 1.12.1 | 2026-08-14 |
v20.1.0 |
A 93/100 | 3 | 1.12.1 | 2026-08-13 |
v20.0.0 |
A 93/100 | 3 | 1.12.1 | 2026-08-12 |
v19.19.1 |
A 93/100 | 3 | 1.12.1 | 2026-08-09 |
v19.19.0 |
A 93/100 | 3 | 1.12.1 | 2026-08-07 |
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 arize-phoenix --online --registry pypiMore in Data Science & ML
MCP server for 2s.io — 575+ pay-per-call tools for AI agents — ground-truth data, AI gateway, and agent infra (storage, locks, queues, watchers). x402 USDC on Base/Solana, no API keys, upto usage billing, free trials.
ArXiv preprints + Google Scholar papers, with citation counts in one query.
Add MCP servers to your favorite coding agents with a single command.
Help agents automatically write and test stories for your UI components
Model Context Protocol server for AI-Archive platform - enables AI agents to discover, submit, and review research papers
MCP server for Semantic Scholar research workflows with stdio and Streamable HTTP transports.