Reexpress SDM Verification
Reexpress MCP Server provides statistical verification for LLM responses using a Similarity-Distance-Magnitude (SDM) estimator that ensembles multiple models (gpt-4.1, o4-mini, text-embedding-3-large) to calculate robust uncertainty estimates against a database of over 100,000 examples. Developed by Reexpress AI for Claude 3.7 Sonnet on Apple silicon Macs, it features dynamic model adaptation through ReexpressAddTrue/ReexpressAddFalse tools, conservative file access controls, and a verification pipeline that processes user questions and AI responses to determine verification probability with calibrated reliability indicators. The server is particularly valuable for software development and data science workflows where users need a statistically robust second opinion on complex LLM outputs.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/reexpressai/reexpress_mcp_server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Reexpress SDM Verification from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.