Public registry of specs AI agents can build from. Search, pull and publish over MCP.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Checks a spec someone is writing against Spekkr's listing rules and returns every problem at once. Pass the text of its spekkr.json. Nothing is saved or published. When it is ready, publish_spec publishes it.
The whole text of the spec's spekkr.json.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http spekkr https://spekkr.com/mcp
Checks a spec someone is writing against Spekkr's listing rules and returns every problem at once. Pass the text of its spekkr.json. Nothing is saved or published. When it is ready, publish_spec publishes it.
| Argument | Type | Description |
|---|---|---|
| manifest* | string | The whole text of the spec's spekkr.json. |
{
"type": "object",
"required": [
"manifest"
],
"properties": {
"manifest": {
"type": "string",
"description": "The whole text of the spec's spekkr.json."
}
},
"additionalProperties": false
}Returns one bounty in full: what the poster wants, how the result is accepted, the reward, the assets it can be paid in, and how far it has got.
| Argument | Type | Description |
|---|---|---|
| id* | string | The bounty's id, as list_bounties gives it. |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "The bounty's id, as list_bounties gives it."
}
},
"additionalProperties": false
}Returns everything Spekkr knows about one spec: its manifest (what it builds, what the person may change under customize, the files, what it needs, the commands and secrets it uses under safety, the changelog). Read it before pull_spec to learn which choices the spec offers. Where the site has found specs like this one, related lists a few: each is another spec, with its own id to call get_spec with, and none of them is part of this one.
| Argument | Type | Description |
|---|---|---|
| id* | string | The spec's id, like username/name. |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "The spec's id, like username/name."
}
},
"additionalProperties": false
}Returns one file of a spec as text. Use it for a file pull_spec listed without content, unless its note says to download it. A long file comes in parts: when the answer has nextLine, call again with that line.
| Argument | Type | Description |
|---|---|---|
| id* | string | The spec's id, like username/name. |
| line | integer | The first line to return. Leave it out to start at the top. |
| path* | string | The file's path, as pull_spec and get_spec list it. |
{
"type": "object",
"required": [
"id",
"path"
],
"properties": {
"id": {
"type": "string",
"description": "The spec's id, like username/name."
},
"line": {
"type": "integer",
"minimum": 1,
"description": "The first line to return. Leave it out to start at the top."
},
"path": {
"type": "string",
"description": "The file's path, as pull_spec and get_spec list it."
}
},
"additionalProperties": false
}Lists the bounties on Spekkr: requests for a spec, an option or an adapter, each with a reward the poster pays directly to whoever takes it. Leave the arguments out to see every bounty. In the answer, total counts the bounties that matched and boardTotal counts every bounty there is.
| Argument | Type | Description |
|---|---|---|
| spec | string | Only bounties that extend this spec, by its id. |
| status | string | Only bounties with this status. Open bounties are the ones still to be taken. |
{
"type": "object",
"properties": {
"spec": {
"type": "string",
"description": "Only bounties that extend this spec, by its id."
},
"status": {
"enum": [
"open",
"claimed",
"submitted",
"verified",
"paid",
"cancelled"
],
"type": "string",
"description": "Only bounties with this status. Open bounties are the ones still to be taken."
}
},
"additionalProperties": false
}Publishes a spec on Spekkr under the signed-in person's username, as username/name, or publishes a new version of one of theirs. Send the text of spekkr.json and every file it lists. A small text file goes in files with its content. Any other file (an image, a PDF, a video, a long document) goes in files with its size in bytes and no content: the answer then gives an address to upload those files to with HTTP PUT, and once they are uploaded you call publish_spec again with the same arguments. Nothing is listed until a call answers with published. A listed spec names the member who published it. A published version never changes: to update a spec, raise the version, add a changelog entry and list every file again. A file that has not changed goes in files with keep set to true and nothing else, and Spekkr takes it from the version listed now, so a screenshot need not be uploaded again. In this version a published spec is free. If anything has to change first, the answer names every problem. This tool needs sign-in. Ask the person before you call it: publishing makes the files public.
| Argument | Type | Description |
|---|---|---|
| files* | array | Every file the manifest lists, every file inside a folder it lists, and every screenshot under demo.screenshots. Leave out spekkr.json, BUILD.md and spekkr.inputs.json. Each file has a path and one of content, bytes or keep. |
| manifest* | string | The whole text of the spec's spekkr.json. Its id is username/name, with the signed-in person's username, and its author.id is that username. |
{
"type": "object",
"required": [
"manifest",
"files"
],
"properties": {
"files": {
"type": "array",
"items": {
"type": "object",
"required": [
"path"
],
"properties": {
"keep": {
"type": "boolean",
"description": "True for a file that is the same as in the version listed now. Give no content or bytes with it."
},
"path": {
"type": "string",
"description": "The file's path inside the spec's folder, like spec.md or shots/home.png."
},
"bytes": {
"type": "integer",
"minimum": 1,
"description": "The file's exact size in bytes, for a file that will be uploaded: one that is not text, or is too long to send as content. Up to 25,000,000."
},
"content": {
"type": "string",
"description": "The file's whole text. For text files of up to 200,000 bytes."
}
},
"additionalProperties": false
},
"description": "Every file the manifest lists, every file inside a folder it lists, and every screenshot under demo.screenshots. Leave out spekkr.json, BUILD.md and spekkr.inputs.json. Each file has a path and one of content, bytes or keep."
},
"manifest": {
"type": "string",
"description": "The whole text of the spec's spekkr.json. Its id is username/name, with the signed-in person's username, and its author.id is that username."
}
},
"additionalProperties": false
}Returns a spec's files, ready to write into a folder and build from: BUILD.md (how to build), spekkr.json (the manifest), spekkr.inputs.json (the person's choices) and the spec files. It checks the choices first and refuses a key the spec does not declare or a value it does not offer. Anything not chosen keeps the spec's default.
| Argument | Type | Description |
|---|---|---|
| id* | string | The spec's id, like username/name. |
| choices | object | The person's choices, by key from manifest.customize: any text for a setting, true or false for an option (on and off are taken too), one of its choices for a swap. For example {"database": "sqlite", "teams": false}. The answer and spekkr.inputs.json write an option as true or false, as the manifest writes its default. |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "The spec's id, like username/name."
},
"choices": {
"type": "object",
"description": "The person's choices, by key from manifest.customize: any text for a setting, true or false for an option (on and off are taken too), one of its choices for a swap. For example {\"database\": \"sqlite\", \"teams\": false}. The answer and spekkr.inputs.json write an option as true or false, as the manifest writes its default.",
"additionalProperties": {
"type": [
"string",
"boolean",
"integer"
]
}
}
},
"additionalProperties": false
}Finds specs on Spekkr by words, the best match first, with each one's id, summary and platforms. Most build a part of an app; a spec that builds something else, such as a CAD model, a circuit or an animation, says so under kind. Search with a few words that name the thing, such as "sign in" or "sliding puzzle"; a slip in a long word is forgiven. When no spec holds every word, the specs that hold some of them are returned and partial is true. Leave query out to list the specs, the ones pulled most first. An answer holds at most limit specs: total counts the specs that matched, and offset reads further into them. catalogTotal counts every spec there is. A spec with publishedBy was published by a member.
| Argument | Type | Description |
|---|---|---|
| kind | string | Only specs of this kind, such as CAD or animation. Each spec names its kind in its own words, so any text is allowed; capitals are ignored. A spec that names no kind builds software. |
| limit | integer | How many specs to return at most. 20 when left out. |
| query | string | Words to look for in a spec's name, keywords, id, kind, stack, summary and platforms. A word may be only the start of one. Small words such as "the" and "for" are left out. |
| offset | integer | How many of the specs that matched to pass over first. 0 when left out. |
| platform | string | Only specs that target this platform. |
Takes one of the signed-in person's specs off Spekkr: its page, its files and its place in search. The versions it had stay used up, so publishing it again needs a higher version. This tool needs sign-in. Ask the person before you call it.
| Argument | Type | Description |
|---|---|---|
| id* | string | The spec's id, like username/name. |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "The spec's id, like username/name."
}
},
"additionalProperties": false
}Says which Spekkr account the caller is signed in as and which specs it has published. This tool needs sign-in: the first call opens a Spekkr page in the browser, where the person signs in with a code sent to their email address and picks a username if they are new.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 17, 2026.
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"description": "Only specs of this kind, such as CAD or animation. Each spec names its kind in its own words, so any text is allowed; capitals are ignored. A spec that names no kind builds software."
},
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1,
"description": "How many specs to return at most. 20 when left out."
},
"query": {
"type": "string",
"description": "Words to look for in a spec's name, keywords, id, kind, stack, summary and platforms. A word may be only the start of one. Small words such as \"the\" and \"for\" are left out."
},
"offset": {
"type": "integer",
"minimum": 0,
"description": "How many of the specs that matched to pass over first. 0 when left out."
},
"platform": {
"enum": [
"web",
"mobile",
"desktop",
"backend",
"cli"
],
"type": "string",
"description": "Only specs that target this platform."
}
},
"additionalProperties": false
}