Lancelot
Lancelot lets an MCP-compatible assistant search and retrieve passages from a local LanceDB document database.
Search documents with
lancedb_searchusing vector, text, or automatic search; returns ranked hits with snippets and sources.Retrieve context for questions with
lancedb_query, returning chunks as one Markdown context block within a character budget.Check database status with
lancedb_status, including connection, tables, row counts, and embedding availability.Report version info with
lancedb_version, including Lancelot version, MCP protocol version, and enabled features.Use read-only tools: the server retrieves and reports data but does not create, modify, or delete database rows; indexing is a separate command.
Run locally over stdio or Streamable HTTP, and deploy via AWS Lambda.
Fall back to local text search without an API key, or use OpenAI embeddings for vector search when configured.
Uses OpenAI's embedding API to turn search queries into vectors for semantic similarity search against a local LanceDB database, enabling vector search (with the embedding model configurable via EMBEDDING_MODEL).
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Lancelot search my docs for the refund policy"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Lancelot
Search your documents from any MCP-compatible assistant. Lancelot connects an agent to a local LanceDB database and returns matching passages with their sources.
Local text search works without an API key.
Vector search uses OpenAI embeddings when configured, with text search as a fallback.
Read-only tools retrieve documents and report database status. Indexing is a separate command.
Stdio and Streamable HTTP support local clients, shared servers and AWS Lambda.
Quickstart · Install · Index documents · Tools · HTTP hosting · Privacy
Quickstart
Requires Node.js 20 or later. First, create a local LanceDB database from your documents
(replace ./docs with a folder containing .md, .txt or .html files):
npx -y --package @ayerselectronics/lancelot lancelot-index ./docs ./lancelot-dbThis creates the documents table in ./lancelot-db for local text search; no API key is needed.
Running it again replaces that table with the folder's current contents.
Then, from the same directory, add the server to Claude Code using that database's absolute path:
claude mcp add --env LANCEDB_PATH="$PWD/lancelot-db" --transport stdio lancelot -- npx -y @ayerselectronics/lancelotAsk Claude to search your documents with lancedb_search. For other MCP clients, see
Install; for table options, see Index your documents.
Related MCP server: Bismut Vector MCP
Try the hosted server
Connect an MCP client to https://mcp.ayers.repair/lancelot to search the public Ayers
documentation. This hosted instance does not read your files. To search your own documents,
run the local server below.
Install
Requires Node.js 20 or later and a LanceDB database folder. If you do not have a database, index a folder of documents first. Use the database's absolute path in your client configuration.
Claude Code, using the stdio form from the Claude Code MCP documentation:
claude mcp add --env LANCEDB_PATH=/path/to/db --transport stdio lancelot -- npx -y @ayerselectronics/lancelot--transport stdio sits between the last --env and the server name on purpose: the CLI reads a
name that follows --env directly as another variable. Everything after -- runs the server.
For vector search, add --env OPENAI_API_KEY=YOUR_KEY before --transport. Your table must contain
vectors created with the configured embedding model. Query text is then sent to OpenAI.
Other MCP clients take the same command in their mcpServers configuration:
{
"mcpServers": {
"lancelot": {
"command": "npx",
"args": ["-y", "@ayerselectronics/lancelot"],
"env": {
"LANCEDB_PATH": "/path/to/db"
}
}
}
}Install links
Open one of these in a browser or on the command line to add the server to the editor. Set
LANCEDB_PATH to your database folder afterwards.
VS Code:
vscode:mcp/install?%7B%22name%22%3A%22lancelot%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40ayerselectronics%2Flancelot%22%5D%2C%22env%22%3A%7B%22LANCEDB_PATH%22%3A%22%2Fpath%2Fto%2Fdb%22%7D%7DCursor:
cursor://anysphere.cursor-deeplink/mcp/install?name=lancelot&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBheWVyc2VsZWN0cm9uaWNzL2xhbmNlbG90Il0sImVudiI6eyJMQU5DRURCX1BBVEgiOiIvcGF0aC90by9kYiJ9fQ==
The link formats are from the VS Code MCP guide and the Cursor install links documentation.
Registry
MCP Registry identity: io.github.ayers-software-repair/lancelot.
Setup command
lancelot-init asks for the database folder and an OpenAI API key, and stores them for later runs.
The key goes to the operating system keychain through keytar, or to an encrypted file when keytar
is not available. Run it with npx -p @ayerselectronics/lancelot lancelot-init. Environment variables
override what it stored.
Index your documents
lancelot-index builds the table the server reads from a folder of .md, .txt and .html
files:
npx -p @ayerselectronics/lancelot lancelot-index ./docs ./db
npx -p @ayerselectronics/lancelot lancelot-index ./docs ./db --table documentsRebuilding replaces the named table. Keep the original documents and choose a separate database folder for each collection you want to manage independently.
It walks the folder and its subfolders (skipping names that start with a dot), strips HTML to
text, and splits each file into chunks of about 1,200 characters on paragraph boundaries. A
paragraph longer than that is cut at a space. Each chunk becomes a row { id, path, title, text }:
id is the relative path and chunk number, path is the relative path, and title is the first
Markdown heading of the file, or the file name. There are no vectors, so search is text search.
--table names the table (default documents). The command replaces that table if it exists, so
running it again rebuilds the table from the folder. It is the only part of the package that writes
to a database; the server never does. Point LANCEDB_PATH at the database folder afterwards.
Tools
Tool | What it does |
| Searches a table and returns ranked hits with short snippets. |
| Retrieves chunks for a question and returns them as one block of context, cut to a character budget. |
| Reports the connection, the tables with row counts, and whether embeddings are available. |
| Reports the Lancelot version, the MCP protocol version of the SDK it is built on, and what is enabled. |
lancedb_search
Parameter | Type | Required | Meaning |
| string | yes | The search text. |
| number | no | Maximum hits, 1 to 200. Default: |
|
| no |
|
| string | no | Table to search. Default: |
| string | no | Column holding the text. Default: |
| string | no | Column holding the vectors. Default: |
The reply is JSON. Its searchType field is the search that produced the hits, vector or
text. When that is not the search you asked for, a note field says why: no API key, the vector
search failed, or (in auto) it found nothing. For vector hits score is the distance, so lower is
closer. For text hits score is the share of query words found in the hit, so higher is better.
Text search is a case-insensitive substring match on the words of the query. It does not use a full-text index and does not stem words.
lancedb_query
Parameter | Type | Required | Meaning |
| string | yes | The question to retrieve context for. |
| number | no | Maximum characters of context. Default: |
| boolean | no | Retrieve a general project overview instead of answering |
| string | no | Table to query. Default: |
| number | no | Maximum chunks to retrieve, 1 to 200. Default: |
The reply is a Markdown block: a header (mode, search type, query), then one section per chunk with its title, source and text. Chunks that would pass the budget are left out and the block says how many.
lancedb_status
Parameter | Type | Required | Meaning |
| boolean | no | Include the column names of each table. Default: false. |
lancedb_version
No parameters.
Table layout
Lancelot reads the text from the text column (text by default). It reads title for the title,
and chunkSource, docSource or path for the source, when a row has them; the first two are the
layout AnythingLLM writes, and path is what lancelot-index writes. Other columns come back as metadata. Vector search needs vectors made with the same model
as EMBEDDING_MODEL.
HTTP mode
npx -y @ayerselectronics/lancelot --http # http://127.0.0.1:3000/mcp
npx -y @ayerselectronics/lancelot --http 8080
npx -y @ayerselectronics/lancelot --http 8080 --host 0.0.0.0 # all interfacesWithout --http the server uses stdio. With it, the server uses MCP
Streamable HTTP.
The SDK negotiates the protocol version with each client. --http takes an optional
port (default 3000). The server binds 127.0.0.1 unless --host names another address, as the
specification advises for a local server. The endpoint is /mcp; any other path is 404.
Origin. The specification says the server must validate the
Originheader. A request that carries anOriginnot listed inLANCELOT_ALLOWED_ORIGINSgets 403. With the variable unset, every request that carries anOrigingets 403. A request with noOriginheader is allowed; an absent header is not an authentication check; the SDK's own origin check refuses those, so Lancelot does the check itself.Host.
LANCELOT_ALLOWED_HOSTSlists theHostheader values that may call, for DNS rebinding protection. Left unset on a loopback bind, it defaults to127.0.0.1:<port>,localhost:<port>and[::1]:<port>. Left unset with--host 0.0.0.0, the Host header is not checked and a warning goes to stderr. A request with a Host not listed gets 403.Stateless. No session id is issued. Each POST gets its own MCP server and transport, closed when the response ends, and answers with one JSON object.
GET(the optional event stream) andDELETE(ending a session) answer 405 withAllow: POST, which the specification permits.Limits. A body over 64 KB is 413. A body that is not JSON is 400.
Protocol version. The
MCP-Protocol-Versionheader is checked by the SDK: a version it does not support is 400, and a missing header is taken as 2025-03-26, as the specification says.
Both variables take comma-separated lists, for example
LANCELOT_ALLOWED_ORIGINS=https://app.example,https://other.example. HTTP mode has no
authentication; the tools are read-only, and a server open to a network should sit behind
something that has it.
AWS Lambda
dist/lambda.js exports handler(event) for an API Gateway HTTP API with
payload format 2.0.
It turns the event into the request the SDK's transport expects and returns
{ statusCode, headers, body }. It reads LANCEDB_PATH, LANCELOT_BASE_PATH (the path the
endpoint is served under, such as /lancelot; unset serves every path) and the two allow-list
variables. The database connection is opened on the first invocation and reused on warm ones. The
function may write only to /tmp, where Lancelot keeps its own settings file.
The Dockerfile builds the
container image on the AWS
Node.js 24 base image for arm64, with the handler dist/lambda.handler. Build dist first:
docker buildx build --platform linux/arm64 --provenance=false -t lancelot-lambda .Environment variables
Settings come from, in order: the environment, the file written by lancelot-init, the defaults.
A variable that is empty or only whitespace counts as not set; the stored value is checked next.
Text search is used when no OpenAI key is available from either source.
Variable | Default | Meaning |
| none | The LanceDB database folder. Required for the tools to work. It must exist; Lancelot does not create it. |
|
| Table used when a call names none. |
|
| Column holding the text. |
|
| Column holding the vectors. |
|
| Hits returned when a call sets no |
|
| Characters of context |
| none | Enables vector search. When unset, the credential store is checked next. |
|
| The OpenAI model used to embed queries. |
|
| Reported by |
|
| One of |
| none | HTTP mode: comma-separated |
| loopback names on the port | HTTP mode: comma-separated |
| any path | Lambda only: the path the endpoint is served under, such as |
Standard output
The MCP stdio transport says the server writes only valid MCP messages to stdout, and that it may write logs to stderr. Lancelot follows that:
Every log level goes to stderr. The logger has one transport, a winston Console transport with all seven levels listed in
stderrLevels.The server entry point points
console.log,console.infoandconsole.debugat stderr, so a library that prints does not corrupt the stream.The server reads stdin until the client closes it, then exits.
HTTP mode keeps the same rule: it writes nothing to stdout either.
lancelot-init and lancelot-index write to stdout. They talk to a person at a terminal and
are never started as a server.
Read-only
The four tools open a table and query it. No code the server runs creates a table, adds, updates or
deletes rows, or builds an index, and the server does not create the database folder if the path is
wrong. The one exception in src is src/bin/lancelot-index.ts, a separate command that builds a
table (see Index your documents); the server never imports it.
tests/readonly.test.ts scans the rest of the source for those calls, and
tests/integration.test.ts compares every database file before and after all four tools run.
Lancelot keeps its own settings and credentials in the per-user configuration directory, never in the database folder.
Privacy
Local text search runs on your machine. When an OpenAI key is available from the environment or your saved credentials, vector search sends query text to OpenAI to compute embeddings. Database contents are returned to the MCP client you connected; that client controls how it uses them. The public hosted endpoint receives the queries you send to it.
Privacy policy and terms: the full statement, including what the hosted endpoint receives.
Development
npm ci
npm run check # typecheck, lint, build, unit and integration testsNode 20 or later. See CONTRIBUTING.md.
License
Apache-2.0. See LICENSE and NOTICE.
Published by Ayers Electronics.
Available Tools
4 toolslancedb_queryCInspect
RAG query with context retrieval from LanceDB
Inputs: question (required), limit, table, warmStart, +1 more.
lancedb_searchCInspect
Search LanceDB for relevant documents using vector or text search
Inputs: query (required), limit, table, searchType, +2 more.
lancedb_statusCInspect
Get LanceDB status and statistics
Inputs: verbose.
lancedb_versionBInspect
Show Lancelot version information
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
lancedb_search and lancedb_query have overlapping retrieval purposes; an agent could easily pick the wrong one without careful reading. The descriptions distinguish them somewhat (raw search vs RAG context retrieval), but the boundary is not crisp. Status and version are clearly distinct.
All four tools use a consistent lancedb_<verb/noun> prefix pattern. Names are readable and predictable throughout.
Four tools is on the thin side but reasonable for a focused retrieval/status server. No obvious bloat, though the surface feels minimal.
The surface only covers search/query/status/version; there is no way to create or ingest documents, list tables, update, or delete data. For a LanceDB server, these are significant lifecycle gaps that would force agents to fail on write/admin tasks.
Maintenance
Related MCP Connectors
Search your AI chat history (ChatGPT, Claude, Codex) from any MCP client. Remote, private, read-only
Query, join, profile, clean and convert CSV/JSON/Parquet with server-side DuckDB over MCP.
Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables MCP hosts like Cursor or Claude to query an enterprise knowledge base via stdio, providing RAG-based answers with cited sources.-
- AlicenseAqualityBmaintenanceEnables any MCP client to index files, directories, and arbitrary text into a local SQLite-backed vector database and perform semantic search with language-aware chunking, filters, and context expansion, all offline without network calls.10MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP clients to query locally indexed code, docs, logs, JSONL/CSV and PDFs using BM25 full-text, vector and hybrid search, returning cited passages with file:line references instead of whole-file reads. Also supports code search, batch queries and persistent agent memory namespaces.19,151Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients such as Claude Code and Cursor to search a documentation corpus, read specific pages, and locally ask grounded questions with verified citations over stdio or Streamable HTTP.MIT