getfund

Export as CSV

getfund_export

Read-only

A link to a CSV of every item of one kind, which Notion's Import > CSV turns into a database with every column and a spreadsheet opens as it is. kind programs: every open program of the catalog, the soonest deadline at the top; matches: the startup's matched programs in fit order, with score, band, why each fits and what to check; perks: every listed perk with its offer, deals, promo codes, redeem steps and partner code, the sponsored one on the top row marked as such. One row per item with the fields of the program and perk lists: multi-values joined with "; ", amounts as plain numbers with a currency column, dates as YYYY-MM-DD, yes or no for a flag. The header row and, for programs and matches, the summary, the getfund page and why each match fits follow locale (en or tr); UTF-8 with a byte order mark. Returns url, which needs no sign-in and works for 10 minutes, expiresAt, kind, rows (the items the file holds now) and columns (its header). A startup gets 10 links in any 24 hours; the next one answers rate_limited. Needs tracker:read and the Autopilot plan.

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": {
      "kind": "<kind>"
    },
    "name": "getfund_export"
  }
}

Input Schema

Name	Required	Default
`kind`	Yes
`locale`	No	en
`startupId`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4/5.0

Behavior5/5

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

Annotations only declare it a safe read, while the description discloses behavior an agent could not otherwise know: the URL needs no sign-in, lives 10 minutes, the quota is 10 links per 24 hours with a rate_limited response, and it requires tracker:read plus the Autopilot plan. It also pins output encoding (UTF-8 with a byte order mark) and the exact return fields.

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

Conciseness3/5

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

Purpose and format details are front-loaded, but the single dense paragraph packs kind semantics, formatting rules, locale, encoding, return shape, quota and permissions into long run-on clauses. A short structured breakdown would let the agent find the permission and quota facts without re-parsing a wall of text.

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

Completeness5/5

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

For a read-only export tool with no output schema, the description supplies the return fields (url, expiresAt, kind, rows, columns), the file format and formatting conventions, auth requirements and rate limits. The only missing piece is which startup startupId selects, which the schema's uuid format partly signals.

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 0%, so the description carries the burden and mostly does: each kind value is expanded with its contents and ordering, and locale is explained as governing the header row, summary, getfund page and match rationale in en or tr. The startupId parameter is never defined — its role is only implied by 'the startup's matched programs' — leaving a real gap for the matches kind.

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

Purpose4/5

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

The opening clause names a specific verb and artifact: 'A link to a CSV of every item of one kind, which Notion's Import > CSV turns into a database.' The three kind values are each described with distinct content, so an agent can tell what will be produced. It stops short of naming sibling tools like getfund_programs or getfund_perks to say why you would export rather than list.

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

Usage Guidelines3/5

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

Usage is implied through the kind descriptions and the mention of a 10-link-per-24-hours cap, which tells the agent this is a heavier, rate-limited path. There is no explicit 'use this when you need a file / Notion import, use getfund_programs when you need live JSON' routing against the many sibling list tools.

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

All getfund 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?