Developer · Local MCP server
Vectora
AI assistant with RAG, web search, filesystem and memory. MCP sub-agent for Claude Code.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.brunosrz/vectora- Version
- 0.1.0rc3
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-05-22
- Updated
- 2026-05-22
- Publisher
- brunosrz (GitHub)
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/brunosrz) · how
- Repository
- github.com/brunosrz/vectora
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | vectora-agent | 0.1.0rc3 | stdio |
How to connect Vectora
Vectora runs locally from a Python package published to PyPI: vectora-agent version 0.1.0rc3. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx vectora-agent. It reads these environment variables: GOOGLE_API_KEY (secret), COHERE_API_KEY (required, secret), TAVILY_API_KEY (required, secret), OPENAI_API_KEY (secret), ANTHROPIC_API_KEY (secret) and LANGSMITH_API_KEY (secret); set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"vectora": {
"command": "uvx",
"args": [
"vectora-agent"
],
"env": {
"GOOGLE_API_KEY": "<secret>",
"COHERE_API_KEY": "<secret>",
"TAVILY_API_KEY": "<secret>",
"OPENAI_API_KEY": "<secret>",
"ANTHROPIC_API_KEY": "<secret>",
"LANGSMITH_API_KEY": "<secret>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| Vector PandaOperate your Vector Panda collections: search and upsert vectors, schema, measured indexes, exports. | Remote · HTTPLive check: sign-in required |
| Vector Panda DocumentationSearch and read Vector Panda docs: API operations, pricing, storage tiers, measured benchmarks. | Remote · HTTPLive check: ✓ handshake |
| Vector Search APIIn-memory vector search with TF-IDF and cosine similarity. x402 micropayment. | Remote · SSELive check: ✗ no handshake |
| Vector Store ScannerProbes vector-database endpoints for unauthenticated exposure of embeddings/RAG data. | Local · stdio |
| VectorCache Semantic Vector CacheX402-gated semantic vector cache for agent swarms: Redis-backed similarity lookup. Paid in USDC. | Local · stdio |
| VectorizeHosted MCP front door to the Vectorize API: raster-to-vector tracing to SVG, PDF, EPS or DXF. | Remote · HTTPLive check: sign-in required |
| VectrSemantic codebase search + persistent working memory for AI code editors. Local, no API key. | Local · stdio, HTTP |
| VelesDB MemoryOffline agentic memory: remember/recall/relate/forget/why over a fused vector+graph+columnar engine. | Local · stdio |