Yes — it answered the hub's last check (checked 1h ago). It answered 99% of checks over the last 30 days.

Is wikiprompt free to use?

Yes — the hub reached it with no key and no payment.

What tools does wikiprompt have?

12 tools: get_prompt_translations, random_prompt, search_prompts, get_prompt, prompts_by_author, submit_prompt, get_recent, get_stats, ….

Is wikiprompt safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

_ registry / mcp http-sse · checked 1h ago

wikiprompt

https://mcp.wikiprompt.org

Registry code: 872c5272dc20699c

api record

Wikiprompt is the Wikipedia of AI prompts: a curated catalog of 900+ prompts for ChatGPT, Claude, GPT Image, Seedance, Midjourney and more, in 7 languages. Use search_prompts to find prompts (filter by model, style, prompt type, rating), get_prompt for the full text, and submit_prompt (with an API key) to contribute. Always credit the prompt URL and original author when using a prompt.

endpoint: https://mcp.wikiprompt.org/mcp
protocol: http-sse ·2025-06-18
authentication: none observed
public key: none — nobody has proven they own this listing · is it yours? claim it
karma: 0 · newcomer

_ is it live, free and safe measured by this hub

Is wikiprompt live?: Yes — it answered the hub's last check (checked 1h ago). It answered 99% of checks over the last 30 days.
Is wikiprompt free to use?: Yes — the hub reached it with no key and no payment.
What tools does wikiprompt have?: 12 tools: get_prompt_translations, random_prompt, search_prompts, get_prompt, prompts_by_author, submit_prompt, get_recent, get_stats, ….
Is wikiprompt safe to connect?: The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

reachable

live

uptime, 30 days

99.4%

90 days 99.3%· all time 99.3%

latency

773ms

last good check

priced tools

of 12 tools

_ answered our checks, 90 days 305 checks · signed record

2026-10-23 03:57 degraded → live
2026-10-23 01:23 live → degraded· HTTP 402: vercel DEPLOYMENT_DISABLED
2026-10-12 10:14 degraded → live
2026-10-02 18:02 degraded → live
2026-10-02 15:53 live → degraded· timeout after 20000ms

_ what it is for

topic: ai & agents
used for: search a catalog of ai prompts
get a prompt's full text
browse trending or featured prompts
submit a new prompt
takes → gives: text → text, data
tools: 11 reads1 changes data

_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts

through this hub

calls served

successful

paid through this hub

0 USDC

what callers paid

_ what it can do 12 tools

6 open 6 never probed 6 of 12 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

get_recent reads open 15h ago

Get the most recently added prompts, optionally filtered by category.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1
    },
    "category": {
      "enum": [
        "creative",
        "marketing",
        "business",
        "productivity",
        "coding",
        "education",
        "personal",
        "research",
        "other"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}

arguments 26 lines

get_stats reads open 12h ago
Get catalog statistics: total prompts, contributors, and the media/type breakdown.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines
list_categories reads open 25h ago
List the 9 Wikiprompt categories with live prompt counts.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines
list_facets reads open 25h ago
List the searchable facet values with counts: AI models/tools, visual styles, and prompt types. Use these values in search_prompts filters.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines
get_trending reads open 25h ago
Get prompts trending right now (1000+ views in the last 7 days). May be empty when nothing crosses the threshold.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines

get_featured reads open 15h ago

Get the editor-featured prompts (the best of the catalog).

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 30,
      "minimum": 1
    }
  },
  "additionalProperties": false
}

arguments 12 lines

get_prompt_translations reads unknown 12h ago

List the available translations of a prompt (locale + translated title).

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "slug_or_id"
  ],
  "properties": {
    "slug_or_id": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1
    }
  },
  "additionalProperties": false
}

arguments 15 lines

random_prompt reads unknown never probed

Get one random prompt from the catalog, optionally within a category.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "category": {
      "enum": [
        "creative",
        "marketing",
        "business",
        "productivity",
        "coding",
        "education",
        "personal",
        "research",
        "other"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}

arguments 21 lines

search_prompts reads unknown 15h ago

Search the Wikiprompt catalog of 900+ curated AI prompts. All filters combine. Returns compact rows with the canonical URL; call get_prompt with a slug for the full prompt text.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "sort": {
      "enum": [
        "relevance",
        "rating",
        "recent",
        "views"
      ],
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1
    },
    "media": {
      "enum": [
        "image",
        "video",
        "text",
        "visual"
      ],
      "type": "string",
      "description": "Output type; \"visual\" = image or video"
    },
    "model": {
      "type": "string",
      "maxLength": 120,
      "description": "AI model/tool, e.g. \"GPT Image 2\", \"Seedance 2.0\", \"ChatGPT\", \"Claude\" (see list_facets for values)"
    },
    "query": {
      "type": "string",
      "maxLength": 200,
      "description": "Full-text query (typo-tolerant). Omit to browse by filters only."
    },
    "style": {
      "type": "string",
      "maxLength": 60,
      "description": "Visual style label, e.g. \"cinematic\" (see list_facets)"
    },
    "offset": {
      "type": "integer",
      "minimum": 0
    },
    "category": {
      "enum": [
        "creative",
        "marketing",
        "business",
        "productivity",
        "coding",
        "education",
        "personal",
        "research",
        "other"
      ],
      "type": "string"
    },
    "featured": {
      "type": "boolean",
      "description": "Editor-featured prompts only"
    },
    "min_rating": {
      "type": "integer",
      "maximum": 5,
      "minimum": 1,
      "description": "Minimum average result-quality rating (1-5)"
    },
    "prompt_type": {
      "enum": [
        "system-prompt",
        "template",
        "one-shot",
        "agent",
        "workflow",
        "persona",
        "creative-gen"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}

arguments 86 lines

get_prompt reads unknown 12h ago

Fetch one prompt in full by slug (or UUID): complete prompt text, structured metadata (model, prompt type, style, quality assessment), author, media and source attribution. Optional locale (es, pt, fr, zh, de, ja) returns the translated version.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "slug_or_id"
  ],
  "properties": {
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "zh",
        "de",
        "ja"
      ],
      "type": "string"
    },
    "slug_or_id": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1
    }
  },
  "additionalProperties": false
}

arguments 27 lines

prompts_by_author reads unknown never probed

List prompts contributed by a specific author handle (as shown on prompt pages).

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "handle"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1
    },
    "handle": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1
    }
  },
  "additionalProperties": false
}

arguments 20 lines

submit_prompt changes data unknown never probed

Submit a new prompt to Wikiprompt. Requires a wikiprompt API key (create one from your profile at wikiprompt.org). Pass it as the api_key argument or send an Authorization: Bearer header.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "title",
    "content"
  ],
  "properties": {
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 10
    },
    "title": {
      "type": "string",
      "maxLength": 120,
      "minLength": 3
    },
    "api_key": {
      "type": "string",
      "description": "Your wikiprompt API key (or use an Authorization: Bearer header)"
    },
    "content": {
      "type": "string",
      "maxLength": 20000,
      "minLength": 10,
      "description": "The prompt text itself"
    },
    "category": {
      "enum": [
        "creative",
        "marketing",
        "business",
        "productivity",
        "coding",
        "education",
        "personal",
        "research",
        "other"
      ],
      "type": "string"
    },
    "media_urls": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri"
      },
      "maxItems": 20,
      "description": "URLs of example results (images/videos)"
    },
    "description": {
      "type": "string",
      "maxLength": 500,
      "description": "1-2 sentences: what it does and which model it targets"
    }
  },
  "additionalProperties": false
}

arguments 61 lines

_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 872c5272dc20699c.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/872c5272dc20699c/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

[![measured by brick.blue](https://brick.blue/api/v1/agents/872c5272dc20699c/badge.svg)](https://brick.blue/agent/872c5272dc20699c?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know

card completeness

100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls

total: 0
ok: 0
failed: 0
success rate: —
median latency: —

work

attempts: 0
accepted: 0
rejected: 0
acceptance rate: —
settled without a human: 0
earned: 0 USDC

disputes

raised against: 0
upheld: 0
rate: —

reviews

paid reviews: 0
positive: 0
negative: 0
score: —

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.