Cartograph
Cartograph gives coding agents ranked file lists, dependency maps, and task-scoped context instead of dumping entire repos into the window. The MCP server exposes three tools: analyze_repo scores files and maps dependencies for local repos or GitHub URLs, get_file_contents fetches specific files after analysis, and build_task_packet returns typed packets with key files, dependency hubs, and validation targets for concrete jobs like bug fixes or feature work. It caches structured artifacts in your user directory so the next agent can pick up from those instead of reanalyzing. Reach for this when you want agents to work with the minimum useful file set rather than context bloat, especially for documentation workflows or targeted fixes where changed_files keeps the surface focused.
- GitHub stars
- 4
- tools
- 3
- transport
- STDIO
- last updated
- Oct 29, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
analyze_repoScore files, map dependencies, and return compact analysis output or embedded top-file contents for a local repo or GitHub URL.
Score files, map dependencies, and return compact analysis output or embedded top-file contents for a local repo or GitHub URL.
No parameter schema in public metadata yet.
get_file_contentsFetch full contents for specific files after analysis.
Fetch full contents for specific files after analysis.
No parameter schema in public metadata yet.
build_task_packetReturn a typed task packet with key files, dependency hubs, validation targets, risks, and task-specific details.
Return a typed task packet with key files, dependency hubs, validation targets, risks, and task-specific details.
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
Cartograph
Cartograph provides task-focused repository context for coding agents. It ships a CLI, an MCP server, install adapters for Claude Code, OpenClaw, and Hermes, and agent assets for documentation workflows.
- npm:
@anthony-maio/cartograph - MCP Registry:
io.github.anthony-maio/cartograph - Quickstart:
cartograph.making-minds.ai
Instead of dumping an entire repository into context, Cartograph ranks the files that matter, maps dependencies, caches structured artifacts, and lets the next tool or agent pick up from those artifacts.
The primary workflow is:
analyzeto map the repopacketto prepare the workcontext --staticto load task-matched files without a model call
wiki, host installs, and benchmarks are secondary surfaces built around that core path.
Install
npm install
npm run build
For global use from npm:
npm install -g @anthony-maio/cartograph
For MCP host discovery via the official registry:
Details
- Repository
- github.com/anthony-maio/cartograph
- Category
- Productivity & Office
- Package
@anthony-maio/cartograph- Transport
- STDIO
- Registry
- MCP registry, active
Related Productivity & Office MCP servers
View all
Smart Context Mcparrayo/smart-context-mcpReduces AI agent token usage by 90% via context compression and task checkpoint persistence.4stars
Presentationsgetalai/alai-mcp-serverGenerate, edit, and export AI presentations to PDF, PPTX, or a shareable link.4stars
eightytwentyh3692/eightytwentyBuilds case-competition and pitch decks in PowerPoint from the layouts behind winning decks.4stars
UK Environmental Intelligence MCP Server from MCPBundlesthinkchainai/mcpbundlesAccess UK flood warnings, river levels, water quality, Met Office forecasts, and carbon data3stars
Contactsmcpaernouddekker/macos-mcpMCP server for macOS Contacts.app — contact management via AppleScript0stars