EU Fund Portal

get_new_winners

Direct feed of young European companies that just received non-dilutive public funding (grants from governments, agencies and research programmes), mostly absent from news and terminals. Each result is a company card: registered name, country, founding year, funder, amount, sector and a one-line "what they do" taken from the funding record (French and German summaries stay in the source language, see whatLanguage). Companies are returned only when their first grant award in our dataset is recent AND the company register shows it was incorporated recently; project vehicles, banks and holdings, mid/large companies and known subsidiaries of corporate groups are removed. Default tier A uses the high-precision sources (Bpifrance i-Lab 2025+ and Innovate UK; German federal projects are tier B until a reliable founding date exists); tier "all" adds noisier ones. "First award" means earliest in our dataset, not necessarily the first ever.

Input Schema

Name	Required	Description
`days`	No	Only companies whose first award in our data started within this many days (default 30, max 365)
`tier`	No	A (default) = high-precision sources only; all = also noisier sources (ADEME, Invest NI, older waves)
`limit`	No	Max companies to return (default 10, max 50)
`country`	No	Two-letter ISO country code of the winner e.g. "FR", "GB", "DE". Omit for all countries
`max_age_years`	No	Maximum company age at the time of the award, in years (default 5, max 50)

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 24, 2026

addedInput schema / properties / tier

Added value: +{
+  "description": "A (default) = high-precision sources only; all = also noisier sources (ADEME, Invest NI, older waves)",
+  "enum": [
+    "A",
+    "all"
+  ],
+  "type": "string"
+}

AddedOct 22, 2026

TDQS

A4.1/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses source coverage per tier, which entity types are filtered out (project vehicles, banks, holdings, mid/large companies, known subsidiaries), and the important caveat that 'first award' means earliest in this dataset, not first ever. That is exactly the kind of non-obvious behavior an agent would otherwise get wrong.

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?

The key scope statement is front-loaded in the first sentence and every subsequent sentence adds verifiable information rather than filler. It is dense, with heavy parentheticals and semicolons, but the length is justified by the total absence of annotations.

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?

No output schema exists, yet the description enumerates the company-card fields returned (name, country, founding year, funder, amount, sector, one-line summary) plus the language caveat, and it explains the filtering logic that determines membership. An agent has everything needed to call it and interpret the results.

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 schema defines all five parameters. The description still adds real meaning: it explains why tier A excludes German federal projects (no reliable founding date), clarifies that 'days' keys off first award in this dataset, and notes the whatLanguage caveat for French/German summaries.

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?

States a specific resource with precise scope: a direct feed of young European companies that just received non-dilutive public funding, with explicit inclusion/exclusion criteria. It is clearly distinct from contract awards and grant search by resource, though it never names a sibling tool to contrast against.

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 tier semantics (A vs all) and the defaults (30 days, tier A), giving the agent a sense of the precision/recall tradeoff. However, there is no explicit 'use this when X, use search_grants or get_grant_details when Y' routing guidance.

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

All EU Fund Portal 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?