Barcelona and Madrid MCP server

• Registry namecom.dondego/wikidata-google-knowledge-mcpverified in the MCP registry

The registry name sits under dondego.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-24
• Tools8
• Server calls itselfwikidata-google-knowledge
• Server version0.3.0
• Protocol version2025-06-18

On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 1576 ms.

• Its tools do none of the product's use cases we checked: Browse what's on today, tomorrow and this weekend; Find free concerts and events in either city.
• Checked on 5 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 5 so far
• What an agent can do with it0 of 2 use cases
• Use45 PyPI downloads a week
• Answeredmeasuring5 of the 7 daily checks it takes to print a share
• Median first answer2340 ms
• Space in an agent's context≈ 2,198 tokensthe definitions of all its tools (8), which an agent carries on every turn
• Tool definitionsB · 85 of 100
• Typed results0 of 8 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 7 of 8

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• kg_search

  Wikidata entity candidates by name, with local place/type filtering. Default 3, maximum 5 candidates. Google and fallback are disabled remotely. New entities use bounded direct-record admission without recursive content certification…

• kg_entity

  Bounded structured facts for one Wikidata QID. Arbitrary source prose, aliases, URLs, media and references are withheld. New entities use bounded direct-record admission without recursive content certification. Identity evidence and…

• kg_related

  Bounded outgoing, inverse or hierarchy relationships for one Wikidata QID. Maximum depth 2 and 10 results. New entities use bounded direct-record admission without recursive content certification. Identity evidence and uncertainty remain…

• kg_resolve

  Canonical deterministic resolution of one identity from supplied local facts and Wikidata evidence. Returns identity verdicts and reason codes, including uncertainty. Google is disabled remotely. New entities use bounded direct-record…

• kg_audit_identity

  Canonical audit of one existing Wikidata QID against one local identity envelope. Returns contradictions, evidence and uncertainty. Provider agreement is not local identity proof. Google crosscheck is disabled remotely. New entities use…

• kg_discover_identity

  Canonical discovery of one identity from a local evidence envelope. Default 3, maximum 5 candidates. Returns ambiguity and insufficient-evidence states; sameAs candidates are unapproved. Google crosscheck is disabled remotely. New…

• kg_lookup_entities

  Compact selected Wikidata facts for at most 10 supplied QIDs. Fact lookup does not establish local identity. New entities use bounded direct-record admission without recursive content certification. Identity evidence and uncertainty…

• kg_status

  Public remote provider configuration and operational limits. No external provider calls. Wikidata is available; Google Knowledge Graph is disabled.