Agents (observee-ai) MCP Server
mcp-agents
PyPI
v0.0.28
Published by observee-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.
A Python SDK for MCP tool integration with LLM providers
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 − 11.7 = 88. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −11.7 | Unsafe deserialization ×4 MTC-SRC-007 | permissions |
2. Client adoption risk — 88 − 1 = 87. 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 |
|---|---|
| −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
medium Unsafe deserialization (observee_agents/search/bm25_filter.py)MTC-SRC-007
In the server's implementation (`observee_agents/search/bm25_filter.py:137`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: cache_data = pickle.load(f) # Verify cache is still valid if cache_data.
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 observee_agents/search/bm25_filter.py
medium Unsafe deserialization (observee_agents/search/local_embedding_filter.py)MTC-SRC-007
In the server's implementation (`observee_agents/search/local_embedding_filter.py:108`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: cached_data = pickle.load(f) if self._verify_cache(cached_data): s
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 observee_agents/search/local_embedding_filter.py
medium Unsafe deserialization (observee_agents_old/search/bm25_filter.py)MTC-SRC-007
In the server's implementation (`observee_agents_old/search/bm25_filter.py:137`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: cache_data = pickle.load(f) # Verify cache is still valid if cache_data.
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 observee_agents_old/search/bm25_filter.py
medium Unsafe deserialization (observee_agents_old/search/local_embedding_filter.py)MTC-SRC-007
In the server's implementation (`observee_agents_old/search/local_embedding_filter.py:110`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: cached_data = pickle.load(f) if self._verify_cache(cached_data): s
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 observee_agents_old/search/local_embedding_filter.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 |
|---|---|---|---|---|
v0.0.28 latest |
B 87/100 | 4 | 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 mcp-agents --online --registry pypiOther implementations of Agents 6
Independent packages implementing the same tool, scanned with the same engine. Compare all 7 side by side →
Model Context Protocol (MCP) Server for the *@inkeep/agents-mcp* API.
Search verified agents and production agent-first AbsoluteJS packages from any MCP client.
An MCP (Model Context Protocol) server for invoking specialized AI agents via any OpenAI-compatible API.
MCP server that wraps AI CLI tools (Claude Code, Gemini CLI, Codex CLI) for use by any MCP client
MCP server for Titanos agents — Super Listing, Amazon lookup, product mining, Seller Central (SP-API), Mercado Livre seller.
MCP server for unified AI agents interface
More in Developer Tools
Hotel booking MCP server — 300K+ properties, real confirmation numbers, loyalty programs. Builders monetize every booking via Stripe Connect. The first MCP server that completes real hotel reservations inside AI conversations.
Manage AdGuard Home through AI assistants
Read-only Azure DevOps for MCP clients using only your existing browser session — no PAT, no Azure CLI. Browse work items, pull requests, comments, attachments and Artifacts feeds across every project, repo and feed you can access.
MCP server for Adobe Experience Manager Assets integration development
Servidor MCP para el tiempo oficial de España (API pública OpenData de AEMET). Predicción, observación y avisos como herramientas MCP tipadas.
A standalone MCP stdio bridge for Affinity by Canva's local MCP SSE server.