jasper_create_ documentSave content as a new Jasper document, so people can open and edit it in the app.
Draft a LinkedIn post in your brand voice, have an Agent write a blog post from a topic, cut a product out of its photo, or ask what to fix first so AI answers cite your brand.
PopMCPJasper
Every endpoint of Jasper's API, plus tools that take an Agent's inputs and a template's fields by name, check them before the run, and hand edited images straight back to your AI.
68 tools in the full catalog: 33 read and 35 write. 40 load by default, and the rest are found with tool search.
jasper_create_ documentSave content as a new Jasper document, so people can open and edit it in the app.
jasper_get_ documentRead one document with its full content.
jasper_get_ usageCount API content generation requests over time, for commands and templates only.
jasper_list_ documentsList documents with id, name, status, owner, project and a short preview of the content.
jasper_list_ projectsList Jasper Projects with id, name, access level and their default voice, audience and style.
jasper_list_ usersList the people in this Jasper workspace with id (usr_...), name and email.
jasper_update_ documentChange a document's text, name, status or project.
jasper_get_ geo_ action_ planSee a brand's AI visibility scores and most severe findings from its latest run.
jasper_get_ geo_ runRead one GEO run, whole or by section.
jasper_get_ geo_ trendsSee how an analysis's scores moved over time, with the key events that help explain it: settings, model, page content and methodology changes.
jasper_list_ geo_ analysis_ summariesSee every GEO analysis with its current scores, share of voice, change against the previous run, prompt count and recommendation count.
jasper_create_ voiceCreate a brand voice from a written description of how the brand sounds.
jasper_get_ audienceRead one audience in full: positioning, value propositions, language patterns, buying triggers and content checklist.
jasper_get_ brand_ contextSee the voices, audiences, style guides, products and knowledge available for on-brand work.
jasper_list_ audiencesList this workspace's target audiences with their id (aud_...), name and description.
jasper_list_ style_ guidesList this workspace's style guides, newest first, with their terms and rules.
jasper_list_ voicesList this workspace's brand voices, newest first.
jasper_clean_ up_ imageRemove objects from an image, using a mask of what to remove.
jasper_composite_ packshotPlace a product on a background with shadows and a reflection.
jasper_decompose_ imageSplit an image into layers using masks.
jasper_remove_ image_ backgroundCut the subject out of an image onto a transparent background.
jasper_remove_ image_ textRemove text laid over an image.
jasper_render_ image_ templateRender an HTML template to an image, changing text, styles and images by element id.
jasper_replace_ image_ backgroundPut a new background behind the subject, from a text description.
jasper_uncrop_ imageExtend an image past its edges, filling in new content.
jasper_upscale_ imageEnlarge an image to a set width and height.
jasper_list_ product_ attributesList the attributes in this workspace's product schema: id (atr_...), name, type, whether it holds a list, and the allowed options.
jasper_list_ productsList Product IQ products with id (prd_...), access level, processing state and attribute values.
jasper_create_ knowledge_ itemAdd a file or text to the Jasper Knowledge Base so generations can use it.
jasper_list_ knowledge_ itemsList Knowledge Base items, newest first, with id (kno_...), name, tags and processingState.
jasper_search_ knowledgeFind Knowledge Base items by meaning, from a natural language question.
jasper_get_ agent_ taskRead one Agent task and its contextItems: the inputs it takes, their types, the allowed options and which are required.
jasper_list_ agent_ tasksSearch the marketing jobs Jasper Agents can do, such as blog posts, research and campaign plans, public and custom.
jasper_run_ agentRun a Jasper Agent task by name, with its inputs by name, checked before the run.
jasper_run_ agent_ streamingRun an Agent task through the streaming endpoint, and keep partial text if it runs long.
jasper_generate_ from_ templateRun a template by name, with required inputs checked first.
jasper_get_ templateRead one template: its inputSchema gives each input's inputKey, type, whether it is required, its maximum length and options.
jasper_list_ templatesList Jasper's default templates and this workspace's custom ones, each with its id, name, description and input keys.
jasper_create_ attachmentHand Jasper a temporary file, text or link as context for one generation.
jasper_generate_ contentWrite content from a plain instruction, on brand.
jasper_create_ projectCreate a Project, optionally with a default voice, audience, style guide and knowledge.
jasper_delete_ documentDelete a document for good.
jasper_delete_ projectDelete a Project for good.
jasper_get_ projectRead one Project with its default settings.
jasper_get_ userRead one person in the workspace.
jasper_update_ projectChange a Project's name, access or default settings.
jasper_create_ geo_ analysisStart tracking a website in AI answers, and queue its first run.
jasper_delete_ geo_ analysisRemove a GEO analysis and stop its scheduled runs.
jasper_get_ geo_ analysisRead one GEO analysis: its scopes, competitors, AI providers, topic clusters with their prompts, schedule and status.
jasper_list_ geo_ analysesList GEO analyses, which track how ChatGPT, Gemini, Claude and Perplexity describe and cite a brand.
jasper_list_ geo_ recommendationsList a run's findings, each with severity, category, affected page and the action to take.
jasper_list_ geo_ runsList an analysis's completed runs, newest first, with runId (aga_...) and date.
jasper_update_ geo_ analysisChange a GEO analysis.
jasper_delete_ voiceDelete a brand voice for good.
jasper_get_ style_ guideRead one style guide with its custom instructions, terms and rules.
jasper_get_ voiceRead one brand voice with its full description.
jasper_update_ voiceChange a brand voice's name, description, metadata or visibility.
jasper_create_ context_ sourceStore a source to attach to a product, such as an image for its Images attribute.
jasper_create_ productCreate a product.
jasper_delete_ productDelete a product for good.
jasper_get_ context_ sourceRead one product source: name, type and value.
jasper_get_ productRead one product with all its attribute values.
jasper_update_ productChange a product's values.
jasper_delete_ knowledge_ itemDelete a Knowledge Base item for good, so generations can no longer draw on it.
jasper_get_ knowledge_ itemRead one Knowledge Base item: name, summary, tags, processingState and, for a link-based item, its original url.
jasper_update_ knowledge_ itemChange a Knowledge Base item's name, summary, tags, metadata or settings, or replace its file.
jasper_run_ agent_ taskRun an Agent task when you already hold the context item ids.
jasper_run_ templateRun a template by id.
Credentials off one Jasper screen, then an endpoint your client signs into. Nothing to deploy, and nothing to install.
Paste an API key from Jasper: open Settings, then Developer tools, then API Tokens at app.jasper.ai/settings/dev-tools/tokens. Only an Admin or Developer can make one, and Jasper's API needs a Business plan with API access. PopMCP checks the key by reading your brand voices. A key reaches one workspace, so there is nothing else to choose.
••••••••••••3f7aGenerating, running Agents and templates, editing images, and changing or deleting anything are writes and wait until an owner or admin allows write actions; new connections start read-only. Agent runs and GEO runs can use credits from your Jasper plan, so tick Jasper on the PopMCP consent screen only for clients that need it.
Drop the PopMCP URL into Claude, ChatGPT, Claude Code, Codex or any other supported client. It signs in through PopMCP with OAuth, so your Jasper credential never leaves the server.
app.popmcp.com/mcpAsk for something harmless before the agent changes anything. Writes run as soon as it calls them, so confirm it reads the right account first.
Write three LinkedIn posts about our new product in our main brand voice for our main audience
jasper_get_brand_contextok
Then just ask for the work
“Write three LinkedIn posts about our new product in our main brand voice for our main audience”
“Have a Jasper Agent write a blog post about AI in retail, then save it as a draft document”
“How visible is our brand in AI answers, and what should we fix first?”
“Take the background off this product photo and put it on a sunny kitchen counter”
“What does our Knowledge Base say about our refund policy? Use it to write a short FAQ answer”
One hosted endpoint, registered once per client. The same tools and the same permissions, whichever window the request comes from.
Add the PopMCP URL under Customize → Connectors and the tools appear in every chat.
The same endpoint, registered in the browser. Nothing to install on the machine you are working from.
Register PopMCP as a custom connector, then let ChatGPT read and update the account.
Wire the endpoint into Codex or the Codex CLI when a task needs live business context, not a fixture.
Register the remote MCP server in OpenCode's config for terminal-first and scripted agent runs.
Add PopMCP as an MCP server in Z.ai's desktop app and work the account from the same window.
FAQ
What teams ask before putting Jasper behind an AI client.
One Jasper API key. Open Settings, then Developer tools, then API Tokens in Jasper, make a token and paste it. Only a workspace Admin or Developer can make one, so anyone else needs to ask them. Jasper's API is available on its Business plan with API access. No developer app is needed. Each key belongs to one workspace, so to work in a second workspace add a second connection with that workspace's key.
Jasper's server is a good fit for generating content and reading your brand context, with a smaller set of tools. This one covers the whole API: it also creates and edits voices, Knowledge, products, Projects and documents, runs templates, edits images and manages GEO analyses. You also get PopMCP's read-only start, team access and one URL for all your connectors.
Agent runs and GEO runs can use credits from your Jasper plan, and the answer reports what a run cost when your workspace meters it. A GEO analysis costs its number of prompts times its number of AI providers, on every run including scheduled ones. Jasper says standard content creation is not what drives credit usage. Reading anything spends none. Jasper's API does not report your balance, so check it in Jasper.
get_brand_context lists your brand voices, audiences, style guides, products and Knowledge in one call. The AI passes the ones you choose to generate_content, run_agent or generate_from_template, and Jasper writes with them. You can also ask it to use your workspace defaults.
run_agent waits for about two minutes. If a task takes longer, the AI is told not to simply repeat it, because the run may already have used credits. run_agent_streaming keeps what was written so far and marks it as unfinished, so a partial answer is never mistaken for the finished one.
Yes, when your plan includes Jasper's Image API. It can remove or replace a background, remove objects or overlaid text, upscale, extend an image past its edges, make a product shot, split an image into layers and render an HTML template. Give it a public link or the file itself, and the finished image comes back in the chat.
Twelve triggers, found by checking on a schedule: documents and Projects created, documents changed, voices, audiences, style guides, Knowledge items and products added or removed, new Agent tasks and templates, a finished GEO run and a new person in the workspace. Jasper's API has no webhooks, so these are not instant.
In PopMCP, yes: a connection starts read-only, so the AI can read your brand context, documents and GEO results and search Knowledge, while generating, Agent runs, image edits, changes and deletes stay blocked until an owner or admin allows write actions. Jasper's API keys have no permission options, and a key can do everything in its workspace.
No. PopMCP hosts it and gives you a Streamable HTTP MCP URL. There is nothing to deploy, no callback URL to register, and no infrastructure to keep running or patch.
Any client that supports a remote Streamable HTTP MCP server: Claude Desktop, Claude Web, Claude Code, ChatGPT custom connectors, Codex and the Codex CLI, OpenCode and Z.ai's ZCode, as well as editors such as Cursor, Windsurf and Zed. Your client signs in to PopMCP with OAuth; the provider credential never leaves the server.
Connect Jasper in PopMCP first, then run claude mcp add --transport http popmcp https://app.popmcp.com/mcp in a terminal. Inside Claude Code, run /mcp and sign in to PopMCP in the browser window it opens, ticking Jasper on the consent screen. The Jasper tools are then available in that session, and no Jasper credential is stored on your machine.
Loading 68 tool definitions into every conversation burns context before the work starts. PopMCP loads a curated 40-tool set covering the everyday workflows and keeps the rest searchable, so your AI pulls a specialist tool only when a task needs it. Every tool stays searchable, and on Scale the owner can load the full catalog for a teammate's connection.
A tool is something your AI calls, and there are 68 here. A trigger is something PopMCP watches for you: 12 Jasper events that can start work on the PopMCP side. Triggers never enter your AI client's context, and none of them ask you to paste a callback URL into Jasper.
Launch a hosted MCP endpoint for Jasper, keep tool access under control, and start testing real workflow prompts right away.