{"name":"io.github.bleedmode/dearuser","slug":"bleedmode-dearuser","title":"Dear User","description":"Tells you how you and your Claude agent actually work together. Local-only, no API keys.","url":"https://mcp.market/server/bleedmode-dearuser","rating":null,"grade":"B","score":80,"certified":false,"status":"active","category":"ai","tags":["ai"],"presence":{"score":22,"stars":0,"forks":0,"downloads_week":78,"last_push_at":"2026-08-07T07:10:32.000Z","license":"MIT"},"uptime":null,"claimed":false,"transport":"npm","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/bleedmode/dearuser","website":"https://dearuser.ai","version":"1.0.20","remotes":[],"packages":[{"registryType":"npm","registryBaseUrl":"https://registry.npmjs.org","identifier":"@poisedhq/dearuser-mcp","version":"1.0.20","runtimeHint":"npx","transport":{"type":"stdio"}}],"tools":[{"name":"collab","description":"Analyze your human-agent collaboration. Scans your agent contract (CLAUDE.md or AGENTS.md), memory files, hooks, skills, and more to produce a collaboration report with persona detection, scoring, friction analysis, and recommendations. Returns a pre-formatted markdown report. Use the format parameter to control detail level: - \"text\" (default): concise, plain-language report designed for non-tech","write_action":false,"price_micros":0,"input_schema":null},{"name":"dismiss_recommendation","description":"Mark a Dear User recommendation as dismissed so it won't be suggested again. Call this when the user picks \"drop\"/\"ikke for mig\"/\"skip\" for a specific recommendation from the action menu. Use recommendation_id from the latest report's menu. For security/health findings, the dismissal propagates to the underlying finding in the ledger so future scans won't re-surface it (unless dismiss_expires_at e","write_action":false,"price_micros":0,"input_schema":null},{"name":"feedback","description":"Send a short note to the Dear User team \\u2014 a bug, a request, a \"this score feels wrong\", or anything you want the founder to read. Zero friction: one tool call and you're done. Behavior: - POSTs your message to the Dear User feedback inbox (Supabase) over HTTPS. - Respects Dear User's local-first guarantee \\u2014 this is the one place data leaves the machine. - Email is only attached when opt_","write_action":true,"price_micros":0,"input_schema":null},{"name":"health","description":"Check the health of your AI stack. Returns a 0-100 system-sundhed score with category breakdown, plus findings ranked by severity. Complement to collab: where collab scores how well you and the agent communicate, health scores whether your skills, hooks, scheduled tasks, and MCP servers are still hanging together or have started drifting apart. Detects: - **Orphan scheduled jobs** \\u2014 task prod","write_action":false,"price_micros":0,"input_schema":null},{"name":"help","description":"Show Dear User's capabilities to the user. Call this whenever the user asks \"what can Dear User do?\", \"hvad kan DearUser?\", \"show me the options\", \"help\", or seems uncertain about which tool fits their need. Also call proactively the first time a user mentions Dear User if they haven't used it before. What this tool does NOT do: - Does NOT run any analysis \\u2014 it only describes what Dear User c","write_action":false,"price_micros":0,"input_schema":null},{"name":"history","description":"Retrieve past Dear User reports without re-running the scan. Reads from local SQLite (~/.dearuser/dearuser.db) \\u2014 no network, no fresh scan. Use when the user wants to see their latest score, how scores have changed over time, or what got better/worse since the last run. A fresh scan takes ~30s; this returns instantly. Call `collab`/`health`/`security` instead if the user explicitly asks for a","write_action":false,"price_micros":0,"input_schema":null},{"name":"implement_recommendation","description":"Apply a Dear User recommendation to the user's setup \\u2014 automatically if safe, or by returning the exact command/instruction for the agent to run. After a collab/health/security report runs, the result text contains a \"Three things to fix\" menu with up to 3 recommendation_ids plus \"Take all of them\" and \"Skip for now\" options. Present those options to the user via AskUserQuestion (or as a numb","write_action":false,"price_micros":0,"input_schema":null},{"name":"onboard","description":"Conversational setup. Walks the user through 5 steps (intro \\u2192 goals \\u2192 stack+pains \\u2192 substrate \\u2192 plan) and produces a tailored setup plan \\u2014 tailored agent-contract template (CLAUDE.md or AGENTS.md), skill recommendations, hook recommendations, and next 3 steps. How to use (for the agent): 1. First call: no arguments. The tool returns an intro question + nextStep. 2. Present","write_action":false,"price_micros":0,"input_schema":null},{"name":"security","description":"Security audit of your AI setup. Scans for: - **Leaked secrets** \\u2014 API keys, tokens, credentials in CLAUDE.md / AGENTS.md, memory, skills, or settings - **Prompt-injection surfaces** \\u2014 hooks/skills that pass user input to shell unsafely - **Rule conflicts** \\u2014 your agent contract says one thing but a hook/skill does another (e.g., \"never force-push\" but a hook runs `git push --force`","write_action":false,"price_micros":0,"input_schema":null},{"name":"share_report","description":"Generate a public shareable link for your Dear User Wrapped card. Uploads an anonymized copy to dearuser.ai and returns a URL you can paste anywhere (X, LinkedIn, Slack). Only Wrapped reports are shareable. Collab/health/security reports stay local. Privacy contract: - Absolute filesystem paths are collapsed to basenames. - Email addresses are stripped. - Anything matching our secret-scanner patte","write_action":false,"price_micros":0,"input_schema":null},{"name":"wrapped","description":"Generate your Dear User \\u2014 shareable stats about your human-agent collaboration in a fun, Spotify Wrapped-style format. What this tool does NOT do: - Does NOT share anything automatically \\u2014 it generates text you can copy/paste if you choose - Does NOT access external accounts or profiles - Does NOT store or upload the generated stats anywhere IMPORTANT \\u2014 Presenting results: The user ","write_action":false,"price_micros":0,"input_schema":null}],"scan":{"score":80,"grade":"B","scanned_at":"2026-09-27T21:49:39.799Z","report":{"scannerVersion":"0.1.9","scannedAt":"2026-09-27T21:49:39.713Z","components":{"code":{"score":20,"max":25,"notes":["5 source files scanned"]},"reliability":{"score":-1,"max":20,"notes":["no gateway calls yet and no remote to probe"]},"poisoning":{"score":-1,"max":15,"notes":["tools not inspected (local package is not executed); not counted"]},"auth":{"score":12,"max":15,"notes":["local package, no credentials required"]},"maintenance":{"score":12,"max":15,"notes":["last push 52 days ago"]},"identity":{"score":8,"max":10,"notes":["registry namespace matches repository owner","GitHub account older than a year"]}},"findings":[{"id":"exec.eval","severity":"medium","component":"code","title":"eval / new Function used","evidence":"dist/index.js: …ode, sch); const makeValidate = new Function(`${names_1.default.self}`, `${names_1.de…"}],"inputs":{"packages":[{"registryType":"npm","identifier":"@poisedhq/dearuser-mcp","version":"1.0.20","found":true,"license":"MIT","hasInstallScripts":false,"dependencyCount":6,"publishedAt":"2026-05-01T06:20:29.932Z","repositoryUrl":"git+https://github.com/bleedmode/dearuser.git","weeklyDownloads":78}],"repo":{"found":true,"owner":"bleedmode","repo":"dearuser","archived":false,"pushedAt":"2026-08-07T07:10:32Z","stars":0,"forks":0,"openIssues":2,"ownerType":"User","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/165356247?v=4","ownerCreatedAt":"2024-03-29T04:38:30Z","license":"MIT"},"icon":{"url":"data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 40 40'%3E%3Ccircle cx='20' cy='20' r='20' fill='%23EC5329'/%3E%3Cpath d='M 11 22 Q 20 32 29 22' stroke='%23FDFBF6' stroke-width='2.5' stroke-linecap='round' fill='none'/%3E%3C/svg%3E","source":"site"},"presence":{"stars":0,"forks":0,"downloadsWeek":78,"license":"MIT","lastPushAt":"2026-08-07T07:10:32.000Z","score":22}}}},"grade_history":[],"reviews":[]}