Mode VC Atlas: TCV Partner & Fund Intelligence

Send a pitch to Mode VC

apply_to_mode_vc

Sends a founder's pitch to the Mode VC team (pre-seed and seed AI companies, checks of US$1M to 5M; see get_mode_vc_thesis_and_criteria). This tool shares data: the founder name, email, company, one-line pitch, stage and deck link go to Mode VC. Show the founder exactly what will be sent and set consent to true only after they agree. Set office_hours to true to also ask for a 20-minute call. Same intake as the form at https://modevc.com/contact. Nothing is shared with anyone outside Mode VC.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "founder_name": "<founder_name>",
      "email": "<email>",
      "company": "<company>",
      "one_liner": "<one_liner>",
      "consent": "<consent>"
    },
    "name": "apply_to_mode_vc"
  }
}

Input Schema

Name	Required	Description
`email`	Yes	Email the founder wants Mode VC to reply to.
`stage`	No	Round being raised.
`company`	Yes	Company name.
`consent`	Yes	Must be true: the founder has seen these details and agreed to send them to Mode VC.
`deck_url`	No	Optional link to the deck (http or https).
`one_liner`	Yes	One sentence on what the company does and for whom (up to 300 characters).
`founder_name`	Yes	Founder's full name.
`office_hours`	No	True to ask for a 20-minute office hours call.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 6, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag non-read-only, open-world and non-idempotent, but the description adds what those annotations cannot: exactly which fields go to Mode VC, that consent must be shown and affirmed by the founder, and that nothing is shared outside Mode VC. This is precisely the PII-disclosure context an agent needs before a one-way external submission.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and target recipient are front-loaded in the first sentence, and every sentence addresses either fit, data handling, or a parameter. The privacy point is restated slightly ('goes to Mode VC' then 'nothing shared with anyone outside Mode VC'), a minor redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-way, open-world submission of personal data, the description covers recipients, consent gating, optional office hours, and the equivalent web form. It omits what the founder sees afterward (confirmation, recipient response, timing), which matters since there is no output schema to explain the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% so the baseline is 3; the description goes further by enumerating the fields transmitted and imposing a workflow rule on `consent` (true only after the founder agrees) and a purpose for `office_hours`. It doesn't add format constraints beyond the schema, so it isn't a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Sends a founder's pitch to the Mode VC team') plus concrete scope (pre-seed/seed AI, US$1M-5M checks). It explicitly routes to the sibling get_mode_vc_thesis_and_criteria for criteria, so an agent can distinguish the two without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context for use (pitching Mode VC, mirroring the contact form) and names the thesis tool as the prerequisite/alternative for checking fit. It never states exclusions, e.g. what to do if the founder is past seed, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Mode VC Atlas: TCV Partner & Fund Intelligence tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?