Send MCP

1. Install the SDK

   Node.js

   npm install @scalekit-sdk/node

   Python

   pip install scalekit

   Full SDK reference: Node.js | Python

2. Set your credentials

   Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

   .env

   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>

3. Authorize and make your first call

   Node.js

   quickstart.ts

   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   
   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENV_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions
   
   const connector = 'sendmcp'
   const identifier = 'user_123'
   
   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Send MCP:', link)
   process.stdout.write('Press Enter after authorizing...')
   await new Promise(r => process.stdin.once('data', r))
   
   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'sendmcp_get_image_gallery',
     toolInput: {},
   })
   console.log(result)

   Python

   quickstart.py

   import os
   from scalekit.client import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()
   
   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENV_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions
   
   connection_name = "sendmcp"
   identifier = "user_123"
   
   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Send MCP:", link_response.link)
   input("Press Enter after authorizing...")
   
   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="sendmcp_get_image_gallery",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)

What you can do

Connect this agent connector to let your agent:

• Feedback submit — Sends feedback about Send itself to the team that builds it
• Skill manage — Create, update, delete, or pin a user-defined skill for this workspace
• Sites manage — Read or change the settings of an existing site or document made with Send that the user owns, given its share id or URL
• Getsite records — Fetch an existing Send site or document by share URL or share ID
• Get skills, image gallery — Fetches skills by ID, lists available skills, or semantically searches them
• Editsite records — Modifies a Send site or document the user previously created or shared with Send

Tool list

Use the exact tool names from the Tool list below when you call execute_tool. If you’re not sure which name to use, list the tools available for the current user first.

sendmcp_complete_upload#Confirms a direct-to-storage upload completed successfully. Call this after uploading to the presigned URL returned by create_presigned_upload. Returns the registered file ID that can be referenced in documents as <img src="asset:{fileId}">. This is step two of the two-step image upload flow.7 params▾

Confirms a direct-to-storage upload completed successfully. Call this after uploading to the presigned URL returned by create_presigned_upload. Returns the registered file ID that can be referenced in documents as <img src="asset:{fileId}">. This is step two of the two-step image upload flow.

NameTypeRequiredDescription

bucketstringrequiredThe storage bucket used for the upload. Returned as part of the presigned upload response from create_presigned_upload.

filenamestringrequiredThe original filename of the uploaded file. Must match what was passed to create_presigned_upload. Example: 'hero-image.png'.

keystringrequiredThe storage key (path) used for the upload. Returned as part of the presigned upload response from create_presigned_upload.

mime_typestringrequiredThe MIME type of the uploaded file. Must match what was passed to create_presigned_upload. Example: 'image/png'.

sizenumberrequiredThe final file size in bytes after the upload completed.

heightintegeroptionalImage height in pixels. Provide when the uploaded file is an image. Pass null for non-image files.

widthintegeroptionalImage width in pixels. Provide when the uploaded file is an image. Pass null for non-image files.

sendmcp_create_presigned_upload#Creates a presigned upload target URL so files can be uploaded directly to storage. This is step one of the two-step image upload flow. Call this first to get the presigned URL, upload the file directly to that URL, then call complete_upload to confirm the upload and register the file.2 params▾

Creates a presigned upload target URL so files can be uploaded directly to storage. This is step one of the two-step image upload flow. Call this first to get the presigned URL, upload the file directly to that URL, then call complete_upload to confirm the upload and register the file.

NameTypeRequiredDescription

filenamestringrequiredThe original filename of the file to upload. Example: 'hero-image.png'.

mime_typestringrequiredThe MIME type of the file. Example: 'image/png', 'image/jpeg', 'image/webp'.

sendmcp_createsite#Creates a Send site or document — a shareable HTML page. Making one takes two calls. First call — intent only. One line on what the user is making and why. Nothing is created. Returns any skills this workspace expects you to follow — brand rules, layouts, tone — and an intentId. Second call — html plus that intentId. See the html field for format requirements. To copy an existing site instead of writing one, pass sourceShareId (share ID or URL) with no html.5 params▾

Creates a Send site or document — a shareable HTML page. Making one takes two calls. First call — intent only. One line on what the user is making and why. Nothing is created. Returns any skills this workspace expects you to follow — brand rules, layouts, tone — and an intentId. Second call — html plus that intentId. See the html field for format requirements. To copy an existing site instead of writing one, pass sourceShareId (share ID or URL) with no html.

NameTypeRequiredDescription

htmlstringoptionalThe complete, self-contained HTML document to publish. Return ONLY raw HTML. No markdown, no code fences, no explanation. Single file: <body> then <style> then <script>. Start with <!DOCTYPE html>, then <html>, <head>, <body>. Zero external dependencies — pure CSS and vanilla JS only. Wrap each section in <section></section>. Fully responsive, mobile-first. Every interactive element must work. Reference images as <img src="asset:{fileId}"> — do not base64-encode. Every <a href> link: use target="_blank" rel="noopener noreferrer". For icons, use <i data-lucide="name"></i>.

intentstringoptionalOne line on what the user is making. ALWAYS send it alone first — no html. Returns any matching skills + an intentId.

intentIdstringoptionalALWAYS pass this back unchanged on the second call. Returned by the first; links the request to what got made.

sourceShareIdstringoptionalThe share ID or URL of an existing document to copy. When provided, the new document starts as an exact copy of the source — do not pass html.

titlestringoptionalTitle of the document. Something short and simple that describes the document.

sendmcp_editsite#Modifies a Send site or document the user previously created or shared with Send. Use whenever the user asks to change, tweak, fix, reword, restyle, add to, or remove anything from an existing site or document — even when they don't name Send or say the word 'edit'. Edits via deterministic string replacement. Requires at least one entry in edits — instruction alone does nothing. If you don't already have the site's current bytes, call GetSite first. Edits apply sequentially against an in-memory copy; if any edit fails, none are persisted. As a last resort after repeated edit failures, fullHtml replaces the whole site while keeping the same share URL — prefer it over recreating with CreateSite, which forks a new share URL.5 params▾

Modifies a Send site or document the user previously created or shared with Send. Use whenever the user asks to change, tweak, fix, reword, restyle, add to, or remove anything from an existing site or document — even when they don't name Send or say the word 'edit'. Edits via deterministic string replacement. Requires at least one entry in edits — instruction alone does nothing. If you don't already have the site's current bytes, call GetSite first. Edits apply sequentially against an in-memory copy; if any edit fails, none are persisted. As a last resort after repeated edit failures, fullHtml replaces the whole site while keeping the same share URL — prefer it over recreating with CreateSite, which forks a new share URL.

NameTypeRequiredDescription

shareIdOrUrlstringrequiredThe site's share ID (8-character alphanumeric string) or full URL. Returned by CreateSite or GetSite.

codeEditstringoptionalOptional raw code edit string.

editsarrayoptionalEdits to apply, in order. Each subsequent edit sees the result of the prior. Atomic: if any edit fails, none are persisted. Each object must include old_string (exact text to replace, with enough surrounding context to be unique, byte-for-byte) and new_string (replacement text, or empty string to delete). Optionally set replace_all to true to replace every occurrence.

fullHtmlstringoptionalLast resort. Replaces the entire document with this HTML while keeping the same share URL. Only use after edits has failed repeatedly and you cannot construct a matching old_string — prefer targeted edits; regenerating a document from memory can silently drop content. Do not pass together with edits.

instructionstringoptionalOptional brief description of the intended change. Recorded for analytics only — does NOT perform the edit on its own. You must still pass edits.

sendmcp_get_image_gallery#Returns all workspace images with proxy URLs for display in the gallery UI. Each item includes an optional description for model context (not shown in the UI). No parameters required.0 params▾

Returns all workspace images with proxy URLs for display in the gallery UI. Each item includes an optional description for model context (not shown in the UI). No parameters required.

sendmcp_get_skills#Fetches skills by ID, lists available skills, or semantically searches them. Skills were previously called 'guidelines', and users may also say 'template' — when the user mentions making, editing, searching, or using a Send skill, guideline, or template, they mean these. Skills shape how sites are created — brand systems, layout patterns, doc-type playbooks. Workspace skills (created by this team) outrank Send skills (official, send/* ids) when both fit. With id: returns the skill including its full content — pass an array of ids to load several in one call. With query: semantic search — describe what the user is making and get the best-matching skills grouped by source with similarity scores. Neither: returns a list of all available skills (name and description only), workspace skills first.2 params▾

Fetches skills by ID, lists available skills, or semantically searches them. Skills were previously called 'guidelines', and users may also say 'template' — when the user mentions making, editing, searching, or using a Send skill, guideline, or template, they mean these. Skills shape how sites are created — brand systems, layout patterns, doc-type playbooks. Workspace skills (created by this team) outrank Send skills (official, send/* ids) when both fit. With id: returns the skill including its full content — pass an array of ids to load several in one call. With query: semantic search — describe what the user is making and get the best-matching skills grouped by source with similarity scores. Neither: returns a list of all available skills (name and description only), workspace skills first.

NameTypeRequiredDescription

idstringoptionalID of the skill to load, or an array of IDs to load several at once. Returns full content.

querystringoptionalNatural-language description of what the user is making. Returns the best-matching skills ranked by similarity. Ignored when id is provided.

sendmcp_getsite#Fetch an existing Send site or document by share URL or share ID. Returns the full HTML source and metadata; the response includes shareId for EditSite or CreateSite (copy mode).1 param▾

Fetch an existing Send site or document by share URL or share ID. Returns the full HTML source and metadata; the response includes shareId for EditSite or CreateSite (copy mode).

NameTypeRequiredDescription

shareIdOrUrlstringrequiredThe document's share ID (8-char alphanumeric string), slug (e.g. 'my-proposal-RaU0Kud4'), or full URL (e.g. 'https://send.co/a/RaU0Kud4').

sendmcp_manage_images#Unified image management tool. Controls what the user sees (upload area, image gallery) and what image data is fetched. Pass ids to fetch specific images by ID; omit ids to fetch all recent images; pass an empty array [] to skip fetching (UI-only mode). Use showUpload to display a drag-and-drop upload area. Use showGallery to control gallery visibility.3 params▾

Unified image management tool. Controls what the user sees (upload area, image gallery) and what image data is fetched. Pass ids to fetch specific images by ID; omit ids to fetch all recent images; pass an empty array [] to skip fetching (UI-only mode). Use showUpload to display a drag-and-drop upload area. Use showGallery to control gallery visibility.

NameTypeRequiredDescription

idsarrayoptionalWhich images to fetch. Omit to fetch all recent images. Pass specific IDs to fetch only those images. Pass an empty array [] to skip fetching entirely (UI-only mode).

showGallerybooleanoptionalShow the image gallery. Defaults to true when fetching images (ids is omitted or has values), false when ids is an empty array [].

showUploadbooleanoptionalShow the drag-and-drop upload area for the user to upload new images. Default is false.

sendmcp_manage_sites#Read or change the settings of an existing site or document made with Send that the user owns, given its share id or URL. Actions: 'documentation' returns the current contract — every supported setting, usage guidance, and a token required for updates; 'get' returns the site's current settings; 'update' applies the settings passed in changes. Call action 'documentation' for a site before your first update to it in a conversation, and include the returned token in update calls. The set of supported settings is defined by the documentation, not by this description.4 params▾

Read or change the settings of an existing site or document made with Send that the user owns, given its share id or URL. Actions: 'documentation' returns the current contract — every supported setting, usage guidance, and a token required for updates; 'get' returns the site's current settings; 'update' applies the settings passed in changes. Call action 'documentation' for a site before your first update to it in a conversation, and include the returned token in update calls. The set of supported settings is defined by the documentation, not by this description.

NameTypeRequiredDescription

actionstringrequiredWhat to do. Start with 'documentation' before the first update to a site in a conversation.

idstringrequiredSend share id (8-char alphanumeric) or full /a/ URL of the site or document.

changesobjectoptionalFor 'update': the settings to change, as described by the documentation action. Pass only the keys you want to change.

docsTokenstringoptionalFor 'update': the token returned by the documentation action for this site.

sendmcp_manage_skill#Create, update, delete, or pin a user-defined skill for this workspace. Skills were previously called 'guidelines', and users may also say 'template' — a user asking to create, edit, delete, or pin a guideline or template means this tool. Call this only when the user explicitly asks for it — not during document creation. create: provide name, description, and content. update: provide id and any fields to change. delete: provide id. pin/unpin: provide id — a pinned skill is returned for every site this workspace makes, not only the ones a search matches; limited to workspace owners and admins.5 params▾

Create, update, delete, or pin a user-defined skill for this workspace. Skills were previously called 'guidelines', and users may also say 'template' — a user asking to create, edit, delete, or pin a guideline or template means this tool. Call this only when the user explicitly asks for it — not during document creation. create: provide name, description, and content. update: provide id and any fields to change. delete: provide id. pin/unpin: provide id — a pinned skill is returned for every site this workspace makes, not only the ones a search matches; limited to workspace owners and admins.

NameTypeRequiredDescription

actionstringrequiredAction to perform. Only call this tool when the user has explicitly asked to create, edit, delete, or pin a skill — never as part of creating or editing a document.

contentstringoptionalFull skill content — instructions, code samples, asset refs, example doc URLs.

descriptionstringoptionalShort description of the skill's purpose

idstringoptionalSkill ID (required for update and delete).

namestringoptionalSkill name (required for create).

sendmcp_showcontent#Embeds Send-managed content inline in the chat. Pass type 'doc' with the shareId to render a published HTML document inline so the user can view it. Call this after CreateDocument or EditDocument when the user should see the result. Requires the user to be signed in to Send.2 params▾

Embeds Send-managed content inline in the chat. Pass type 'doc' with the shareId to render a published HTML document inline so the user can view it. Call this after CreateDocument or EditDocument when the user should see the result. Requires the user to be signed in to Send.

NameTypeRequiredDescription

idstringrequiredThe Send share ID (8-char alphanumeric string) or full /a/ URL of the document to display. Returned by CreateDocument. Example: 'RaU0Kud4' or 'https://send.co/a/RaU0Kud4'.

typestringrequiredComponent type to embed. Only 'doc' is currently supported — renders a published Send HTML document inline in the chat.

sendmcp_submit_feedback#Sends feedback about Send itself to the team that builds it. Call it when the session produces something the team would genuinely want to know: the user explicitly asks to send feedback or report a problem, aims praise or frustration at Send, Send can't do something the user wants and it matters to them, or you form a strong opinion worth volunteering. Most sessions produce none — ordinary friction is not signal. When you do call it, context is the entire value: what the user was making, what they expected, and what happened instead. Not for feedback about Claude, or about anything that isn't Send. Only include detail the user is ok with sharing as feedback.5 params▾

Sends feedback about Send itself to the team that builds it. Call it when the session produces something the team would genuinely want to know: the user explicitly asks to send feedback or report a problem, aims praise or frustration at Send, Send can't do something the user wants and it matters to them, or you form a strong opinion worth volunteering. Most sessions produce none — ordinary friction is not signal. When you do call it, context is the entire value: what the user was making, what they expected, and what happened instead. Not for feedback about Claude, or about anything that isn't Send. Only include detail the user is ok with sharing as feedback.

NameTypeRequiredDescription

feedbackstringrequiredWhat the Send team should know. Be specific: what broke, what confused, or what worked well.

sentimentstringrequiredWhether this is praise, a problem, or both. Praise is signal too — send it.

areastringoptionalWhich part of Send this is about, if it's clear.

contextstringoptionalWhat was being made and what was expected. The concrete details are what make this actionable.

shareIdstringoptionalOptional. Share ID of the site involved, if any — a new user may not have one, and that's fine.