Contextful
This is an alpha-stage context engine that indexes your codebase once and returns ranked, cited evidence packs instead of making agents repeatedly read dozens of files. It exposes seven MCP tools, anchored by context_pack(query, budget, scope), which replaces scattered grep and file read calls with a single token-budgeted response. You also get search_code forlex/BM25 search, trace_path for graph traversal across symbols and modules, impact_analysis for reverse dependencies, and write_lesson for storing evidence-backed memory that persists across sessions. Uses SQLite with FTS5 for local-only indexing. Set it up with npx @inferensys/contextful init, then run it as an MCP server. Reach for this when context window bloat and redundant file reads are slowing down your agent workflows.
- GitHub stars
- 1
- tools
- 7
- transport
- STDIO
- last updated
- May 15, 2026
Tools
7 toolsPublic tool metadata for what this MCP can expose to an agent.
context_packReturns a ranked, cited, token-budgeted bundle instead of forcing 40 random file reads.
Returns a ranked, cited, token-budgeted bundle instead of forcing 40 random file reads.
No parameter schema in public metadata yet.
search_codePowerful code, docs, symbol, and memory search.
Powerful code, docs, symbol, and memory search.
No parameter schema in public metadata yet.
trace_pathGraph traversal across files, symbols, modules, and config.
Graph traversal across files, symbols, modules, and config.
No parameter schema in public metadata yet.
impact_analysisReverse dependencies and likely tests.
Reverse dependencies and likely tests.
No parameter schema in public metadata yet.
why_changedCurrent evidence plus git history.
Current evidence plus git history.
No parameter schema in public metadata yet.
recall_memorySearch session learnings and durable project lessons.
Search session learnings and durable project lessons.
No parameter schema in public metadata yet.
write_lessonStore an evidence-backed memory.
Store an evidence-backed memory.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
contextful cover image
Contextful
⚠️ This is in early alpha. The API, features, and integrations are not stable. Expect breaking changes. Feedback & contributions are very welcome!
Local Context Management + Search Engine + Memory for Agentic AI.
Contextful is a runtime contextual layer and local search engine for agents that gives them one fast way to find, compress, cite, and remember project context.
Available as a CLI-first tool with an MCP runtime bridge and generated agent instructions, it integrates seamlessly with Codex, Claude Code, Cursor, Windsurf, GitHub Copilot, VS Code, Cline, Roo Code, Continue, and Zed.
Contextful screenshotInstead of making an agent read 40 files every session, Contextful indexes the project once and returns a ranked, cited, token-budgeted context pack.
Why?
Details
- Repository
- github.com/inferensys/contextful
- Website
- inferensys.github.io/contextful
- Categories
- AI & LLM Tools, Search & Web Crawling
- Package
@inferensys/contextful- Transport
- STDIO
- Registry
- MCP registry, active
More from inferensys
Related AI & LLM Tools MCP servers
View all
AI Scanneraakashbhardwaj27/ai-scanner-mcpScan codebases for LLM/AI SDK usage, exposed API tokens, and hardcoded secrets.1stars
Revettr Mcpalexanderlawson17/revettr-pythonCounterparty risk scoring for agentic commerce via x402 micropayments.0stars
Dingdawg Code Reviewdingdawg/dingdawg-agent-1AI code review — security, quality, performance. Learns your patterns. Receipted.0stars
Llmconveyorsebenezer-isaac/llmconveyors-mcp53 tools for LLM Conveyors: job hunting, B2B sales, ATS scoring, resume tools.1stars
MeteoSwiss MCP Servereins78/meteoswiss-llm-toolsSwiss weather data for AI assistants — forecasts, measurements, stations, pollen.0stars
Guardrailsexpertvagabond/guardrails-mcp-serverAI Agent Guardrails MCP server - security layer1stars