Compare two AI tools side by side
Put any two skills or MCP servers next to each other: risk grade, what each can access, how popular it is, and how to install it.
| What | mcpso | mcp-code-graph |
|---|---|---|
| Risk grade | BB · Some risk signals Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee. | CC · Moderate risk signals Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee. |
| Type | App connector | App connector |
| Est. context load | ~850 tokens / turn (~5 tool schemas, 0.43% of 200k context) | ~500 tokens / turn (~3 tool schemas, 0.25% of 200k context) |
| GitHub stars | 2.1k | 402 |
| Weekly npm downloads | — | 724 |
| Local files | Reads & writes local folders | No local folder access noted |
| Command execution | No shell command runner noted | Runs shell or system commands |
| Network reach | Connects to outside service API | Connects to outside service API |
| Credentials | Requires API key or token | No API token required |
| Package source | GitHub (chatmcp/mcpso) | npm (mcp-code-graph) |
| Install command | Source repo only | npx -y mcp-code-graph |
| Bottom line | mcpso is a directory tool itself, but the real risk comes from installing unvetted MCP servers from it—each one can potentially access or exfiltrate data depending on its permissions and the source's trustworthiness. | mcp-code-graph is distributed via npm (mcp-code-graph); review its source code, dependencies, and requested permissions before use. |
Based on public adoption and transparency signals as of Oct 29, 2026. Our opinion, not a code audit or security guarantee.
Go deeper
Want to inspect exact published files, install hooks and network hosts?
Run a pre-install check on any package, MCP config or SKILL.md, or open a full report with PDF export.