Gokulanand

What an agent can do with the common-context-mcp corpus

Gokulanand-art/common-context-mcp: common context MCP: shared, append-only context store for AI agents over MCP: checkpoints, failures, file claims, handoffs and crash…

• Look up how common-context-mcp implements agent-memory, ai-agents, claude-code, with answers cited to file and line.
• Reuse a worked example: the commit “3.10.0: Muse enforcement hooks like Claude” (7 files · JavaScript, TypeScript).
• Answer from common-context-mcp's real JavaScript source instead of memory (AI, prompts and agents).

• Where does common-context-mcp handle “3.10.0: Muse enforcement hooks like Claude”?
• How does common-context-mcp implement agent-memory?
• What does test do in common-context-mcp?

Search the GitHub repository Gokulanand-art/common-context-mcp with XERJ (https://hub.xerj.org/corpus/gokulanand-art--common-context-mcp).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/Gokulanand-art/common-context-mcp common-context-mcp && git -C common-context-mcp checkout 313e8dc891ab0eef04088ce64a0ac2380cffd65b
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./common-context-mcp --url http://127.0.0.1:9200 --prefix common-context-mcp --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

corpus gokulanand-art--common-context-mcp · AI, prompts and agents
Related corpora: dunorth595--xrpl-did-mcp, fastmcp, dreamforgestudiollc/EMET, kedarvartak/rote
AI search and retrieval with XERJ · Case study: reference coding for agents