Aurelmark API

List EU funding call changes

funding_list_changes

Read-onlyIdempotent

Returns changes to open and forthcoming EU grant calls on the official EU Funding & Tenders Portal: new calls, moved deadlines, status changes and removals, with before/after records. Use it to follow EU grants; use tenders_list_deadline_changes for procurement tenders and compliance_list_deadlines for legal compliance dates. Inputs (all optional, they narrow together): since (YYYY-MM-DD, default 7 days ago), change (added/amended/removed), field (which field changed, e.g. deadlines), identifier (topic or call id prefix, 2 to 200 characters, e.g. HORIZON-CL5-2026), limit (1 to 50, default 20) and cursor (next_cursor, same filters). Output: changes[] with before and after topic records, official topic URL and observed_at, plus count, has_more, next_cursor and feed check time; the Portal is checked about twice a day. A change feed, not a catalogue of all open calls. For one topic's current record use HTTP GET /v1/eu/funding/topics/{id} (see /openapi.json). Terms: read-only; MCP calls are never charged. Without a key, metered routes give 10 successful answers a day free, as short samples (up to 3 records, without file proof, history or paging cursor) where a paid HTTP address exists (unmetered routes are unlimited); errors do not count. On the paid HTTP routes, errors are free, and so are empty answers except a sanctions name search with no match when every loaded list it checks is fresh (lists not loaded yet are named in the answer). An optional API key keeps its prepaid-credit policy. When the free answers run out, the error names the HTTP alternative.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "funding_list_changes"
  }
}

Input Schema

Name	Required	Description
`field`	No	Only changes to this field Allowed: deadlines, status, opens, deadline_model, title, call_title, kind, url; e.g. deadlines.
`limit`	No	Changes per page, 1 to 50 (default 20); e.g. 20.
`since`	No	Changes observed on or after this date, YYYY-MM-DD (default: 7 days ago); e.g. 2026-10-01. Must be a parseable YYYY-MM-DD date.
`change`	No	One kind of change only Allowed: added, amended, removed; e.g. added.
`cursor`	No	Opaque next_cursor from this tool's prior answer; f followed by 1 to 12 digits, e.g. f0. Keep filters unchanged; omit on first call.
`identifier`	No	Topic/call identifier prefix, 2 to 200 ASCII letters/digits or . _ -, e.g. HORIZON-CL5-2026; omit for all topics

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 14, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already cover read-only, idempotent and open-world, and the description goes well beyond them: it discloses refresh cadence (Portal checked about twice a day), pagination behaviour (has_more, next_cursor, cursor keeps filters unchanged), field contents (official topic URL, observed_at, feed check time), and the auth/metering regime including that unkeyed free answers are truncated to 3 records without file proof, history or paging cursor. That truncation detail materially changes how an agent should treat the response, so the extra length earns its place.

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?

Front-loaded well: purpose, sibling routing and the change-feed scoping all land in the first two sentences, and the output/parameter details follow logically. However, the closing metering paragraph is bloated and partly self-repeating ("errors do not count" vs "errors are free"; the free-answer exhaustion sentence restates the HTTP-alternative point), reading like boilerplate appended across many tools rather than content tuned to this one.

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, so the description carries the return-value burden and does so: it enumerates changes[] with before/after topic records, official URL, observed_at, plus count, has_more, next_cursor and feed check time. Combined with cadence, pagination and metering limits, an agent has everything needed to call this correctly and interpret the response.

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 and the description mainly restates defaults and ranges. It does add genuinely useful semantics the schema does not: that all six filters are conjunctive ("they narrow together"), that cursor must be reused with unchanged filters, and that identifier is a 2–200 character topic/call id prefix with a concrete example. That is additive without being redundant.

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 ("Returns changes to open and forthcoming EU grant calls on the official EU Funding & Tenders Portal") and enumerates the change types covered (new, moved deadlines, status changes, removals) with before/after records. It explicitly negates a plausible misreading ("A change feed, not a catalogue of all open calls") and names the sibling resources for tenders and compliance rather than leaving differentiation to inference.

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

Usage Guidelines5/5

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

Gives explicit routing: this tool for EU grants, tenders_list_deadline_changes for procurement tenders, compliance_list_deadlines for legal compliance dates, and HTTP GET /v1/eu/funding/topics/{id} for a single topic's current record. It also states the filter combination semantics ("all optional, they narrow together") so an agent knows how to compose queries.

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

All Aurelmark API 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?