Context Engine

An open-core, self-improving code search platform that indexes codebases into vector embeddings and exposes semantic search via MCP servers. Uses ONNX embeddings, Qdrant vector DB, Redis cache, and an adaptive reranking system that learns from usage patterns. Provides two MCP endpoints: a memory server and an indexer server.

Evaluated Mar 06, 2026 (0d ago) vunknown
Homepage ↗ Repo ↗ Developer Tools mcp code-search semantic-search rag embeddings qdrant self-improving agentic
⚙ Agent Friendliness
63
/ 100
Can an agent use this?
🔒 Security
70
/ 100
Is it safe for agents?
⚡ Reliability
64
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
65
Documentation
65
Error Messages
45
Auth Simplicity
68
Rate Limits
55

🔒 Security

TLS Enforcement
80
Auth Strength
75
Scope Granularity
60
Dep. Hygiene
70
Secret Handling
65

Community/specialized tool. Apply standard security practices for category. Review documentation for specific security requirements.

⚡ Reliability

Uptime/SLA
70
Version Stability
65
Breaking Changes
60
Error Recovery
60
AF Security Reliability

Best When

You have large codebases and want AI agents to find semantically relevant code with citations, and you are comfortable running a multi-service stack (vector DB, embeddings, cache).

Avoid When

Your codebase is small enough for simple text search, or you need a lightweight single-binary solution. The BUSL-1.1 license may also restrict commercial use.

Use Cases

  • Semantic code search across large codebases for AI coding assistants
  • Providing contextual code answers with citations to AI agents
  • Multi-repository code indexing and retrieval
  • Augmenting Claude Code, Cursor, Gemini, or Augment with codebase awareness

Not For

  • Simple keyword-based code search (overkill infrastructure)
  • Small projects where grep/ripgrep suffices
  • Teams unwilling to run multiple services (Qdrant, Redis, embedding server, etc.)

Interface

REST API
Yes
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: session_token
OAuth: No Scopes: No

Optional session-based authentication. Zero-auth mode supported for local/personal use. No API keys required for basic local operation.

Pricing

Model: open_core
Free tier: Yes
Requires CC: No

BUSL-1.1 license (Business Source License). Open-core model with optional cloud service. VS Code extension temporarily unavailable during cloud migration.

Agent Metadata

Pagination
unknown
Idempotent
Unknown
Retry Guidance
Not documented

Known Gotchas

  • Requires running multiple services: Qdrant, Redis, embedding server, LLM decoder, file watcher
  • VS Code extension temporarily unavailable during cloud migration
  • BUSL-1.1 license restricts commercial use without permission
  • Performance benchmarks show moderate accuracy (MRR 0.276 on CoSQA) - not a silver bullet for code search
  • Ports 8000-8003, 8080, 8100-8101, 6333-6334, 6379 all need to be available

Alternatives

Full Evaluation Report

Detailed scoring breakdown, competitive positioning, security analysis, and improvement recommendations for Context Engine.

$99

Scores are editorial opinions as of 2026-03-06.

5208
Packages Evaluated
26151
Need Evaluation
173
Need Re-evaluation
Community Powered