Vectorsearch

io.github.CloudCorpRecordsPublished by GitHub account CloudCorpRecordsv0.1.0Updated Nov 7, 2026

Store and retrieve text in a Qdrant vector database by similarity search.

VerifiedSTDIODesktop onlyDatabasesKnowledge & Memory

Overview

AI-generated overview

A small local memory server that stores text in a Qdrant vector database and retrieves it later by similarity search.

What you can do
  • Store text, with optional metadata, as a point in a Qdrant collection, creating the collection if it does not exist.
  • Find stored entries by plain-language query and get back the closest matches with their payloads and scores.
  • Target a named collection per call, or fall back to a default collection name.
When to use it
Useful when you want an assistant to keep short notes or facts across sessions and look them up later, backed by a Qdrant instance you already run. It suits simple, self-contained recall rather than high-quality semantic search.
Requirements
Runs as a local stdio process via npx or the Docker image. Needs a reachable Qdrant service; QDRANT_URL sets a non-default address (defaults to localhost:6333). COLLECTION_NAME sets the default collection (defaults to documents). No accounts or API keys are declared.
Before you install
Stored text and metadata are written to your Qdrant database, and re-storing the same text updates the existing point rather than adding a duplicate. Similarity comes from a local hash-based embedding with token overlap, not model-grade semantic embeddings, so retrieval quality is limited. Point to a Qdrant instance you trust, since the server sends your text there.

Installation

In SourceWeft

  1. Open Vectorsearch in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

vectorsearch

vectorsearch is a small memory for agents: store a piece of information now, then ask for it back later with a plain-language query. It keeps exactly two operations — store and find — and backs them with a Qdrant vector database over its REST API.

Set QDRANT_URL to reach a non-default service (it assumes http://localhost:6333). The collection used when a call does not name one comes from COLLECTION_NAME and defaults to documents. Storing into a collection that does not exist yet creates it first, sized to this tool's embedding dimension with cosine distance.

Install

bash
npx @reneturcios/vectorsearch find "how do we deploy the staging app"

Or run the container image:

bash
docker run -i ghcr.io/cloudcorprecords/vectorsearch

The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.

CLI

bash
# Store something (optionally into a named collection)vectorsearch store "the staging deploy runs from the release branch" --collection notes
# Ask for it backvectorsearch find "staging deploy" --collection notes
# Start the MCP servervectorsearch mcp
vectorsearch --version

Exit codes: 0 on success, 1 when the service call fails (the error includes the HTTP status), 2 for usage errors.

MCP server

One bin serves both faces. The mcp subcommand starts a stdio MCP server:

bash
npx -y @reneturcios/vectorsearch mcp

MCP client configuration:

json
{  "mcpServers": {    "vectorsearch": {      "command": "npx",      "args": ["-y", "@reneturcios/vectorsearch", "mcp"],      "env": {        "QDRANT_URL": "http://localhost:6333",        "COLLECTION_NAME": "documents"      }    }  }}

Tools

ToolRequiredOptionalPurpose
qdrant-storeinformation (string)metadata (object), collection_name (string)Store some information in the Qdrant database. The text and any metadata become the point payload.
qdrant-findquery (string)collection_name (string)Retrieve relevant information from the Qdrant database. Returns the closest stored entries with their payloads and scores.

About the embeddings

The reference design pairs Qdrant with an external embedding model. This rebuild deliberately calls no external embedding service. Instead it embeds text locally with a deterministic hash-based function: the same text always produces the same unit vector, and texts that share tokens land near each other, which keeps store and find self-consistent and fully offline. Be clear-eyed about the trade-off: this is a local fallback with token-overlap similarity, not model-grade semantic embeddings. Swapping in a real embedding provider later only changes the executor's vector function — the tools, schemas, and storage shape stay the same.

Point ids are likewise deterministic, derived from a hash of the text (and metadata when present), so re-storing the same information updates the same point instead of piling up duplicates.

Development

bash
npm installnpm run build   # tsc -> dist/npm test        # node test runner over test/*.test.ts, fakes only, no live servicenpm run dev     # run the CLI from source via tsx

Dispatch, default-collection resolution, and error propagation are tested against a fake executor; the Qdrant REST executor is tested against a fake fetch that records its requests (collection ensure / create-on-missing, point upsert shape, search mapping).

License

MIT — see LICENSE.

Source: README.md at commit 9626c3d

Tools

2

qdrant-store

Store some information in the Qdrant database

Parametersmetadatainformationrequiredcollection_name

qdrant-find

Retrieve relevant information from the Qdrant database

Parametersqueryrequiredcollection_name

Version history

1
  1. v0.1.0LatestOct 31, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts