Md Md
Lets your AI assistant tap into your team's internal engineering knowledge stored in md.md's versioned Markdown blocks. Exposes tools like resolve_context to inject relevant docs based on task context, plus block lifecycle operations (create, update, publish) and observability calls like list_injection_logs. The server sits between your IDE and md.md's backend, forwarding requests over stdio and handling the resolution logic that figures out which published blocks matter for your current work. Useful when you're tired of re-explaining architecture decisions and coding standards in every prompt and want your team's collective context available on demand.
- tools
- 10
- auth
- Secret needed
- transport
- STDIO
- env vars
- 4
- last updated
- Apr 10, 2026
Tools
10 toolsPublic tool metadata for what this MCP can expose to an agent.
resolve_contextPrimary tools include resolve_context, attach_blocks, list_blocks, get_block, health_check, block lifecycle tools, and access and observability tools.
Primary tools include resolve_context, attach_blocks, list_blocks, get_block, health_check, block lifecycle tools, and access and observability tools.
No parameter schema in public metadata yet.
attach_blocks
No parameter schema in public metadata yet.
list_blocks
No parameter schema in public metadata yet.
get_block
No parameter schema in public metadata yet.
health_check
No parameter schema in public metadata yet.
create_blockBlock lifecycle tool.
Block lifecycle tool.
No parameter schema in public metadata yet.
update_blockBlock lifecycle tool.
Block lifecycle tool.
No parameter schema in public metadata yet.
publish_blockBlock lifecycle tool.
Block lifecycle tool.
No parameter schema in public metadata yet.
whoamiAccess and observability tool.
Access and observability tool.
No parameter schema in public metadata yet.
list_injection_logsAccess and observability tool.
Access and observability tool.
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 languageConfiguration
MD_MD_API_KEY*secretAPI key for md.md backend
MD_MD_API_URLBase URL of md.md backend API
MD_MD_TEAM_IDOptional team scope override
MD_MD_WORKSPACE_IDOptional workspace scope override
Readme
md.md
md.md is a team intelligence platform that turns internal engineering knowledge into versioned Markdown blocks, then injects the right context into AI-assisted development workflows.
It combines:
- A backend registry and policy engine
- A React dashboard for authoring and publishing knowledge blocks
- An MCP server for IDE and assistant integrations
- Integration docs and product design docs
What Problem This Solves
AI coding assistants are strong at general coding but weak on team-specific context. Without shared context, teams repeatedly re-explain standards, architecture decisions, and workflows.
md.md solves this by letting teams:
- Author knowledge once
- Publish stable versions
- Resolve the right context at task time
- Reuse the same context across IDEs and AI tools
Repository Structure
Details
- Repository
- github.com/kedarvartak/md.md
- Category
- Documents & Knowledge
- Package
md-md-mcp-server- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related Documents & Knowledge MCP servers
View all
Mcp Ratchet Clinical Chartingm2ai-mcp-servers/mcp-ratchet-clinical-chartingMCP server for clinical charting with Claude - document patient visits to EMR0stars
Mcp Contradiction Checkonetrueclaude-creator/mcp-contradiction-checkFind where your notes disagree — contradiction detection for markdown vaults.0stars
Lightpaper Mcplightpaperorg/lightpaperAPI-first publishing platform. Publish markdown as permanent web pages with quality scoring.0stars
Plexuspcas-io/plexusTyped on-prem knowledge graph for AI agents — read-only for humans, write-only for agents via MCP.0stars
knowmindschubeler-consulting/knowmindAI agent memory & knowledge graph, hosted in Germany (GDPR). Recall, relations, store via MCP.0stars
Boltworksquidboy30/boltwork-mcpAI services via Bitcoin Lightning — PDF summarisation, code review, translation and more.0stars