Context LensSAFE
Semantic search knowledge base for MCP-enabled AI assistants. Index local files or GitHub repos, query with natural language. Built on LanceDB vector storage. Works with Claude Desktop, Cursor, and other MCP clients.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Give your AI the ability to understand meaning, not just match keywords.
[](https://badge.fury.io/py/context-lens) [](https://www.python.org/downloads/) [](https://opensource.org/licenses/MIT)
What is Context Lens?
Context Lens transforms any content into a searchable knowledge base for your AI assistant. This self-contained Model Context Protocol (MCP) server with built-in serverless vector storage (LanceDB) brings semantic search to your conversations. Point it at any content - codebases, documentation, contracts, or text files - and your AI can instantly understand and answer questions about the content.
Traditional keyword search finds files containing specific words. Miss the exact term? Miss the content.
Context Lens understands meaning. Ask about "authentication" and find code about login, credentials, tokens, OAuth, and access control - even if those files never use the word "authentication."
See It In Action
Want to understand how Context-Lens works? Here's the fun part: you can use Context-Lens to learn about Context-Lens.
Demo: Using Claude Desktop with Context-Lens to index and query this repository itself. No git clone, no scrolling through code - just questions and answers.
Why LanceDB?
Context Lens uses LanceDB - a modern, serverless vector database:
- 🆓 Completely Free & Local - No cloud services, API keys, or subscriptions
- ⚡ Zero Infrastructure - Embedded database, just a file on disk
- 🚀 Fast & Efficient - Built on Apache Arrow, optimized for vector search
- 💾 Simple Storage - Single file database, easy to backup or move
Think of it as "SQLite for AI embeddings" - all the power of vec
5610bd8867dbOBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add context-lens -- None context-lens==0.1.8
Exposed tools (6)
3 read · 1 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
add_document | write | Adds a document or GitHub repository to the knowledge base. |
clear_knowledge_base | destructive | Removes all documents from the knowledge base. |
get_document_info | read | Gets metadata and statistics about a document in the knowledge base. |
list_documents | read | Lists all documents in the knowledge base with pagination support. |
remove_document | destructive | Removes a document from the knowledge base. |
search_documents | read | Searches documents using semantic vector similarity to find relevant content. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
clear_knowledge_base, remove_document
fastmcp, lancedb, sentence-transformers, transformers, torch, numpy, pandas, pyarrow
img/demo.gif
# Load environment variables from .env file
# Load environment variables from .env file
Gates applied: no_behavioural_pass.
5610bd8867dbfull audit observations/trust-audit/mcp-server/cornelcroi__context-lens.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | 5610bd8867db | SAFE | B | 89 | first audit |
Questions
What is the Context Lens MCP server?
Semantic search knowledge base for MCP-enabled AI assistants. Index local files or GitHub repos, query with natural language. Built on LanceDB vector storage. Works with Claude Desktop, Cursor, and other MCP clients.
What tools does Context Lens expose?
6 in total: 3 read-only, 1 that write, and 2 that can delete or overwrite (clear_knowledge_base, remove_document). Every one is listed on this page with its risk.
Is Context Lens safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Context Lens need?
No credential environment variables were found in its source, so it appears to need none.
How does Context Lens run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as context-lens.
How current is this page?
The grade is for one exact copy of the source (5610bd8867db), read on 2026-10-09. The repository is watched and re-audited when it changes.