Productivity · Local MCP server

grad-agent

Autonomous MCP agent for grad school applications: prof discovery, cold emails, SOP, tracking.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.i-ninte/grad-agent
Version
0.2.9
Status
Active
Category
productivity
Transport
stdio (local process)
Package
PyPI
Published
2026-09-25
Updated
2026-09-25
Publisher
i-ninte (GitHub)
Repository
github.com/i-ninte/grad-agent
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPIruntime: uvxgrad-agent0.2.9stdioANTHROPIC_API_KEY (required, secret), SMTP_SERVER (required), SMTP_PORT (required), SMTP_USERNAME (required), SMTP_PASSWORD (required, secret), SMTP_FROM (required), GITHUB_TOKEN (secret), HF_TOKEN (secret), GRAD_AGENT_HOME, LOR_LETTERHEAD_PATH, LOR_LETTERHEAD_WIDTH

How to connect grad-agent

grad-agent runs locally from a Python package published to PyPI: grad-agent version 0.2.9. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx grad-agent. It reads these environment variables: ANTHROPIC_API_KEY (required, secret), SMTP_SERVER (required), SMTP_PORT (required), SMTP_USERNAME (required), SMTP_PASSWORD (required, secret), SMTP_FROM (required), GITHUB_TOKEN (secret), HF_TOKEN (secret), GRAD_AGENT_HOME, LOR_LETTERHEAD_PATH and LOR_LETTERHEAD_WIDTH; set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "grad-agent": {
      "command": "uvx",
      "args": [
        "grad-agent"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<secret>",
        "SMTP_SERVER": "<value>",
        "SMTP_PORT": "<value>",
        "SMTP_USERNAME": "<value>",
        "SMTP_PASSWORD": "<secret>",
        "SMTP_FROM": "<value>",
        "GITHUB_TOKEN": "<secret>",
        "HF_TOKEN": "<secret>",
        "GRAD_AGENT_HOME": "<value>",
        "LOR_LETTERHEAD_PATH": "<value>",
        "LOR_LETTERHEAD_WIDTH": "<value>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More productivity servers

All 3,040 →
ServerRunsEndpoint or package
GorevTask management system for AI assistants with MCP protocol, templates, and bilingual support (TR/EN)Local · stdionpm: @mehmetsenol/gorev-mcp-server
Govtoolspro MCP ServerWorkflow tools for federal contractors: go/no-go scoring, incumbent intel, recompete, NECO.Local · stdionpm: govtoolspro-mcp-server
GpuAgent-to-agent network for teams: dm, who-knows-X routing, shared rooms. Human-in-the-loop.Remote · HTTPjoinmultiplayer.ai
GrabMail disposable emailDisposable email for agents: create an inbox, wait for the message, read the code. No key needed.Remote · HTTPgrabmail.io
GrafanaManage dashboards, users, teams, alerts, data sources, and access control.Local · stdioPyPI: mcparmory-grafana
GranoflowConnect MCP-capable AI agents to local Granoflow tasks, reviews, cards, imports, and work memory.Local · stdionpm: @granoflow/mcp-server
Gravity SwarmAgent reputation network — compute tasks, submit proofs, earn ELO via Nostr MCP.Local · stdionpm: gravity-swarm-mcp
Great QuestionRun user research from any AI tool. Create studies, recruit participants, query insights.Remote · HTTPgreatquestion.co