Afterpaths
Captures session history from Claude Code, Cursor, and Codex CLI, then exposes it through MCP tools for search, summaries, and rule extraction. The server gives agents access to `afterpaths_list_sessions` for browsing past work, `afterpaths_search` to find discussions across transcripts, and `afterpaths_show_artifacts` to trace file provenance. Useful when you want agents to learn from previous sessions without manually writing rules, or when debugging requires context from earlier conversations. Rules get extracted automatically into `.claude/rules/` based on discoveries, dead ends, and decisions. The search tool auto-escalates to raw transcripts when summary searches return nothing, so context doesn't get lost even in older sessions.
- GitHub stars
- 2
- tools
- 6
- auth
- Secret needed
- transport
- STDIO
- env vars
- 2
- last updated
- Apr 27, 2026
Tools
6 toolsPublic tool metadata for what this MCP can expose to an agent.
afterpaths_list_sessionsList recent sessions for context recovery
List recent sessions for context recovery
No parameter schema in public metadata yet.
afterpaths_show_sessionRead session summaries and transcripts
Read session summaries and transcripts
No parameter schema in public metadata yet.
afterpaths_show_artifactsShow artifacts ledger: files written/edited with provenance
Show artifacts ledger: files written/edited with provenance
No parameter schema in public metadata yet.
afterpaths_summarizeGenerate summaries for sessions
Generate summaries for sessions
No parameter schema in public metadata yet.
afterpaths_searchSearch across past sessions (auto-escalates to transcripts on 0 summary hits)
Search across past sessions (auto-escalates to transcripts on 0 summary hits)
No parameter schema in public metadata yet.
afterpaths_get_rulesGet extracted rules (dead ends, decisions, etc.)
Get extracted rules (dead ends, decisions, etc.)
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
ANTHROPIC_API_KEYsecretAnthropic API key for session summarization and rule extraction. Not required for search, list, show, or rules tools.
OPENAI_API_KEYsecretOpenAI API key (alternative to Anthropic) for summarization.
Readme
Afterpaths
Smarter with every session, automatically.
Extract rules from what worked. Track what didn't. Find the best models for your stack.
You're running Claude Code, Cursor and Codex, but which model actually works best for your stack? What approaches lead to breakthroughs vs. expensive dead ends? How do you stop your agents from making the same mistakes?
Afterpaths gives you a single view across all your AI coding tools: compare what's working, capture discoveries as rules, and guide your agent team away from costly diversions.
Afterpaths Demo
What you're seeing:
ap audit— Overview of your sessions, models used, and rule statusap show 5 --raw— Raw session transcript (the messy JSONL data, made readable)ap show 5— LLM-generated summary extracting discoveries, dead ends, and decisionshead .claude/rules/gotchas.md— Rules automatically extracted and ready for Claude's next session
The Problem
You're managing multiple agents - retaining critical context and learning from sessions is painful:
Details
- Repository
- github.com/burnssa/afterpaths
- Website
- github.com/burnssa/afterpaths
- Categories
- AI & LLM Tools, Search & Web Crawling
- Package
afterpaths- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Wisdomgraphcklam12345/wisdomgraphNeo4j-native DIKW memory for Claude Code — knowledge that compounds across sessions2stars
LittleSis API Servercode-rabi/littlesis-mcpProvide access to the LittleSis API to track corporate power and accountability. Enable querying and exploring relationships and entities related to corporate i2stars
Meertrackmeertrack/meertrack-mcpCompetitive intelligence - track what competitors ship each week. 8 tools, 3 prompt workflows.2stars
Kit.com MCP Serverdancumberland/kit-mcpAgent-optimized MCP server for Kit.com email marketing. 13 composite tools, 100% V4 API.2stars
A2CRa2cr/a2crSave AI-agent handoff checkpoints, WorkStash notes, and WorkThreads in a local A2CR workspace.2stars