Loading…
Lineage-gated agent memory tools on Postgres + pgvector, enforced by row-level security.
amu-pgvector is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 78/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding amu-pgvector to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
uvx amu-pgvector==0.1.3Review the upstream source before running this command.
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-09-30T21:00:35.50614Z",
"publishedAt": "2026-09-30T21:00:35.50614Z",
"statusChangedAt": "2026-09-30T21:00:35.50614Z"
}
},
"server": {
"name": "io.github.sangaraju1988/amu-pgvector",
"title": "amu-pgvector",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "0.1.3",
"packages": [
{
"version": "0.1.3",
"transport": {
"type": "stdio"
},
"identifier": "amu-pgvector",
"runtimeHint": "uvx",
"registryType": "pypi",
"registryBaseUrl": "https://pypi.org",
"packageArguments": [
{
"type": "positional",
"value": "amu-pgvector-mcp"
}
],
"runtimeArguments": [
{
"name": "--from",
"type": "named",
"value": "amu-pgvector[mcp]==0.1.3",
"description": "Installs with the [mcp] extra, required for the amu-pgvector-mcp console script's mcp SDK dependency (it's optional at the base-package level so the Python client and LangChain integration don't pull it in unnecessarily)."
}
],
"environmentVariables": [
{
"name": "AMU_PGVECTOR_DSN",
"isSecret": true,
"isRequired": true,
"description": "Postgres DSN for the role this server runs as. Results are gated by row-level security under this exact role -- use an amu_writer-member role for amu_record/amu_check_conflict, or an amu_agent_base-member role for read-only amu_search."
},
{
"name": "AMU_PGVECTOR_EMBEDDING_DIM",
"description": "Embedding vector dimension, used only by the built-in deterministic fallback embedder when sentence-transformers (the amu-pgvector[st] extra) isn't installed. Must match the dimension sql/amu_pgvector.sql was installed with. Default: 1536."
}
]
}
],
"repository": {
"url": "https://github.com/sangaraju1988/amu-pgvector",
"source": "github"
},
"description": "Lineage-gated agent memory tools on Postgres + pgvector, enforced by row-level security."
}
}