MCP server that maintains a concept map, decision records, and freshness checks to provide persistent project context beyond code.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We ran the install command below but it didn't respond within our test window β this can mean a slow first-time install rather than a real problem.
npx -y -pNo response to initialize.
This is an experimental automated check and can have false negatives β missing environment variables, a slow cold install, etc. It doesnβt necessarily mean somethingβs wrong. Last checked 1mo ago.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Mason.
mason_initStart here.** Returns the Map-Reduce setup playbook. Idempotent.
mason_complete_initMarks the project as initialized once the playbook is done.
generate_snapshot_batchMap step β returns one batch of files for the assistant to summarize.
save_partial_snapshotPersists the partial map for one batch.
reduce_snapshotReduce step β returns every partial + instructions to merge into a unified map.
save_snapshotPersist the final unified map. Clears partials.
Remember why decisions were made Β· Catch outdated guidance Β· Find what else needs updating
Install on macOS or Linux:
Windows PowerShell:
No Node or npm required. Git is required. The installer configures PATH for Bash, Zsh, and Windows. Platform details Β· npm installation
Run this in your Git repository (open a new terminal if the installer asks):
Setup connects MCP, hooks, and project instructions. Review your host's trust settings, start a new session, and give your agent a normal task.
Check that Mason is being used:
Setup uses your installed mason commandβno project launch scripts or runtime copies. Status distinguishes configuration from observed use. Setup and upgrades Β· Disconnect a project Β· Other MCP clients
The audit checks claims in README and agent instruction files throughout the repository. The review checks committed changes against your chosen base. Both are read-only and need no model calls.
| As your project grows⦠| Mason helps by⦠|
|---|---|
| Instructions fall behind the code. | Flagging missing paths, incorrect workspace counts, and missing npm scripts. |
| A patch misses a related update. | Surfacing references, related tests, and files that historically change together. |
| Old decisions lose their context. | Retrieving recorded rationale and review status, and flagging changes to the code they apply to. |
| A repair gets interrupted. | Retaining the original findings and verifying them through the final documentation commit. |
After resolving an incident or settling a constraint, ask your agent to record the reason with Mason. Later tasks can retrieve it. Proposals and accepted decisions stay distinct.
Mason complements tests, linters, and code review. Findings are evidence to inspect; unavailable checks stay explicit.
Earlier read-only decision-retrieval evaluations scored 9.0/10 with Mason vs 7.0/10 without. The initial ten-task patch comparison tied at 10/10 for both. Improved patch outcomes remain to be demonstrated. Results, methodology, and limitations
Factual signals from GitHub, npm, and our automated checks β not a rating.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/adrianczuczka-mason)<a href="https://allmcps.com/mcp/adrianczuczka-mason"><img src="https://allmcps.com/api/badge/adrianczuczka-mason?style=directory" alt="Mason on AllMCPs" /></a>