Autonomous MCP agent for grad school applications: prof discovery, cold emails, SOP, tracking.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
An autonomous MCP agent that helps you apply to fully funded MS and PhD programs.
Discover and draft
run_program_batch)identity ambiguous: 2 comparable candidates, h=40 vs h=38) is persisted to a skipped sheet for audittarget_regions: [US, Canada] in your profile; keyword table + homepage TLD + LLM fallback)MISMATCH if they may have moved labs) and flags researchers who have not published in 2+ yearsLearn and follow through
outcome_report shows what works)Track everything
Runs as a stdio MCP server for Claude Code / Claude Desktop / any MCP client, or as a plain CLI.
Published on:
grad-agentio.github.i-ninte/grad-agentPick one:
This writes:
~/.grad-agent/profile.yaml β your identity, projects, preferences~/.grad-agent/programs.yaml β target programs (seeded)~/.grad-agent/scholarships.yaml β external scholarships with deadlines (seeded)~/.grad-agent/.env β secrets templateFill in ~/.grad-agent/.env:
Fill in the important bits of ~/.grad-agent/profile.yaml:
name, identity_line, portfoliocv_path, transcript_path (absolute paths)degree_status: bachelors | masters (drives PhD eligibility gating)target_term, target_degreeresearch_areas: [nlp, ai4health, ...]target_regions: [US, Canada] β only draft for profs in these regions (empty = anywhere)seed_projects: 3 to 10 flagship projects with name, pitch, link, tagsProfile edits apply immediately, even while a long-running MCP session is open.
Then:
Three commands, in order:
On Windows you may need to open a new PowerShell or Terminal window after
pipx ensurepath for the PATH change to take effect.
Prefer a zero-install one-liner? Skip pipx and use uvx:
Then in a new Claude Code session:
You should see grad-agent connected with ~36 tools. Before it does anything useful, run grad-agent init (or uvx grad-agent init) and fill in ~/.grad-agent/.env and ~/.grad-agent/profile.yaml as described in the setup section above.
If you skipped pipx ensurepath, grad-agent register-claude prints an absolute-path variant of the command that works without PATH changes.
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
The uvx command needs no prior install. If you already ran pipx install grad-agent,
you can use "command": "grad-agent", "args": ["server"] instead.
Any other MCP client (Cursor, Zed, Windsurf) uses the same manifest shape; just
point them at uvx grad-agent server.
The package ships scheduler templates for all three OSes. grad-agent schedule
emits the right one for your platform:
Then follow the install instructions the command prints. In case you want them up front:
macOS (launchd):
Linux (systemd user timer, fires at 08:00 local):
Windows (Task Scheduler):
Or import the XML via the Task Scheduler GUI (Action β Import Task).
Every morning: replies auto-detected via IMAP, follow-up nudges drafted for silent profs, 3 identity-verified faculty leads with fit scores (best fit first), hooks fact-checked against paper abstracts, freshness warnings when a prof's S2 record and live homepage disagree, plus program and scholarship deadline warnings β all in one review email. Skipped leads are persisted with the specific mismatch reason (view with skipped_log_view or open the skipped sheet).
| Tool | Purpose |
|---|---|
run_daily_batch(n, area) | Full pipeline: verify β recruiting β hook + verify β draft β log |
outreach_log_view(limit) | Show last N rows of the outreach xlsx |
outreach_mark_sent(prof, uni) | Flag a row as actually sent to the prof |
sync_catalog(source) | Pull projects from github, hf, or local |
list_projects_in_catalog() | Show every project the matcher can see |
list_programs() | Your target programs |
upcoming_deadlines(days) | Any program deadline in the next N days |
lor_add / lor_outstanding / lor_mark | Recommendation-letter tracker |
run_program_batch(program_id, n) | Deadline-driven batch: draft for one program's faculty |
skipped_log_view(limit) | Audit trail of skipped leads with the specific stage + mismatch reason |
s2_cache_invalidate(query, all) | Selectively purge Semantic Scholar cache entries by author name or id |
followups_due(days) | Drafted nudges for profs silent 10+ days |
outreach_mark_followup(prof) | Record a sent nudge (never nudged twice) |
outreach_mark_response(prof, outcome) | Tag replies; feeds the matcher's learning loop |
outcome_report() | Response rates by area and project |
ingest_replies() | Read-only IMAP scan; auto-tags replies in the log |
interview_prep(prof) | One-page brief: their papers, likely questions, your talking points |
list_scholarships(region) | External scholarships filtered by eligibility region |
upcoming_scholarship_deadlines(days) | Scholarship deadlines approaching |
draft_cold_email(...) | Manual per-prof draft |
draft_sop(...) | Compile a Columbia-style SOP PDF (versioned: sop_v1, v2, ...) |
send_draft_to_me(path) | Ship any draft file to your review inbox |
discover_profs(area) | arXiv + OpenReview scan (raw candidates, no verification) |
Blog publishing tools (publish_article, update_article, ...) are gated behind blog.enabled: true in profile.yaml and are specific to the author's Turso-backed Next.js portfolio. Most users can ignore them.
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/grad-agent)<a href="https://allmcps.com/mcp/grad-agent"><img src="https://allmcps.com/api/badge/grad-agent?style=directory" alt="Grad Agent on AllMCPs" /></a>