grad-agent
Autonomous MCP agent for grad school applications: prof discovery, cold emails, SOP, tracking.
The current version, v0.2.5, was published to the official MCP registry on 2026-07-14. It is distributed as grad-agent on PyPI, filed under Email by this index, and declares 9 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; the index's current counts put this record in context.
Using grad-agent in Claude, Cursor, Gemini CLI, Cline, or Zed?
MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).
Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less
uv tool install mcpindex-gate && mcpindex-config-wireSemantic screen found no manipulation pattern in the description. Conformance probe not yet run.
mcpindex.integrity.descriptionpassINFOevidence“No malicious instructions found”via static_description
- - Semantic screen only - the deterministic conformance probe has not run on this server
- - Confidence is reported but not yet calibrated (v1)
- - Screen reads the tool description, not the live behavior
- - advisory
- - registry description only no input schema
- - screen model 8b
- - Still current: the description we screened is unchanged, re-checked against the registry
Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.
Own this server? Screen its description →
That verdict was true at screening time (snapshot 2026-08-21).
Contracts can change after screening, with no version bump. The gate pins grad-agent’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.
See your first HOLD in 2 minutes →
Related: how to trust an MCP server · screen before install · silent contract drift
People vet a server before wiring it in. One line on your project site or docs answers that with an independent record: screening verdict, registry provenance, contract drift history. It stays current as new screens and drift events land.
[Independent trust record for grad-agent](https://mcpindex.ai/server/io-github-i-ninte-grad-agent) - screening verdict, registry provenance, and contract drift monitoring.<a href="https://mcpindex.ai/server/io-github-i-ninte-grad-agent">Independent trust record for grad-agent</a> - screening verdict, registry provenance, and contract drift monitoring.A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.
[](https://mcpindex.ai/server/io-github-i-ninte-grad-agent)<a href="https://mcpindex.ai/server/io-github-i-ninte-grad-agent"><img src="https://mcpindex.ai/api/v1/badge/io-github-i-ninte-grad-agent" alt="mcpindex verdict" height="20" /></a>ANTHROPIC_API_KEYAnthropic API key used by Claude Haiku for hook synthesis and verification.
SMTP_SERVERSMTP host for the review mailer.
SMTP_PORTSMTP port.
SMTP_USERNAMESMTP username; used as From address by default.
SMTP_PASSWORDSMTP password. Gmail App Password recommended.
SMTP_FROMEnvelope From address for drafts emailed to the user's review inbox.
GITHUB_TOKENOptional. Personal access token used to enumerate the user's public and private GitHub repos during catalog sync.
HF_TOKENOptional. HuggingFace token used to enumerate the user's published models and datasets during catalog sync.
GRAD_AGENT_HOMEOptional. Override the default ~/.grad-agent/ location for profile, programs, secrets, and data.
Email inbox API for AI agents: read, search, draft, send, and triage mail over Streamable HTTP.
Read, search, send, organize, draft and schedule email across your inboxes from any MCP client.
Music promo platform: email campaigns, Instagram DMs, Spotify discovery, SmartLinks, analytics.