Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/screenpipe/screenpipe/llms.txt

Use this file to discover all available pages before exploring further.

Continue is an open-source AI coding assistant with 20k+ GitHub stars. it works in VS Code and JetBrains IDEs, and supports MCP servers for external context.

​
setup

1

Install Continue

install Continue from the VS Code marketplace
2

Open Continue settings

click the gear icon in Continue’s panel
3

Edit config.json

edit ~/.continue/config.json and add:
{
  "mcpServers": [
    {
      "name": "screenpipe",
      "command": "npx",
      "args": ["-y", "screenpipe-mcp"]
    }
  ]
}
4

Restart VS Code

restart VS Code to load the MCP server
ensure screenpipe is running on localhost:3030 before using Continue with screenpipe.

​
usage

once configured, Continue can access your screen history: recall what you were working on: 
> @screenpipe what was I working on this morning?
find error messages: 
> find the error I saw in my terminal and help me fix it
reference documentation: 
> what documentation was I reading about react hooks?
clipboard history: 
> I copied some code earlier, can you find it?
meeting context: 
> what did we discuss about the API in standup? help me implement it

​
context providers

Continue also supports custom context providers. you can add screenpipe as a context provider for more control: 
{
  "contextProviders": [
    {
      "name": "screenpipe",
      "params": {
        "apiUrl": "http://localhost:3030"
      }
    }
  ]
}
with a context provider, you can:
  • add screenpipe context automatically to every query
  • customize how screenpipe data is fetched
  • create custom context filters
MCP integration is simpler and recommended for most users. use context providers if you need custom behavior.

​
available tools

via MCP, Continue gets access to:

​
search-content

search screen OCR, audio transcriptions, and input events:
  • filter by content type (all, ocr, audio, input, accessibility)
  • time range filtering
  • app/window filtering
  • speaker filtering for audio

​
export-video

create video exports from screen recordings.

​
activity-summary

get app usage statistics for a time range.

​
list-meetings

list detected meetings with context. see MCP server documentation for full details.

​
example workflows

code with context: 
user: I was looking at how another project handles authentication,
      find that code and help me implement something similar

Continue: [searches screenpipe, finds code, suggests implementation]
recall errors: 
user: there was a typescript error earlier about types,
      find it and explain how to fix it

Continue: [searches screen history, finds error, explains solution]
meeting follow-up: 
user: what did we discuss in the standup about the API changes?
      help me implement those changes

Continue: [searches audio, extracts requirements, writes code]
reference API documentation: 
user: find the API docs I was reading about the /users endpoint
      and write a client function

Continue: [searches screen history, finds docs, implements client]

​
tips for best results

use the @screenpipe mention: 
✅ "@screenpipe what was I working on this morning?"
✅ "@screenpipe find error messages from my terminal"
be specific about what you want: 
✅ "find the React component I was reading about this morning"
✅ "show me the error from my terminal 30 minutes ago"
✅ "what docs was I reading in Chrome about async/await"

❌ "find that thing I saw" (too vague)
mention the app when relevant: 
✅ "what was I looking at in Chrome"
✅ "show me VS Code windows from earlier"
✅ "find my Slack messages about the deploy"
use time references: 
✅ "this morning"
✅ "in the last 2 hours"
✅ "yesterday afternoon"
✅ "during my 3pm meeting"

​
VS Code vs JetBrains

both IDEs support Continue with screenpipe, but there are some differences:
featureVS CodeJetBrains
MCP support✅ full support✅ full support
config location~/.continue/config.jsonIDE settings
performancefasterslightly slower
context providers✅ supported✅ supported
recommendation: both work great, use whichever IDE you prefer.

​
troubleshooting

Continue not finding screenpipe?
  • verify screenpipe is running: curl http://localhost:3030/health
  • check config.json syntax is valid (valid JSON)
  • restart your IDE after config changes
queries returning no data?
  • ensure screenpipe has screen recording permissions
  • check screenpipe has been running and recording
  • verify the time range has data: curl "http://localhost:3030/search?limit=1"
  • try a broader time range
MCP connection errors?
  • ensure Node.js >= 18.0.0 is installed
  • try npx clear-npx-cache
  • check IDE’s logs for error messages
@screenpipe mention not working?
  • verify the MCP server is configured (not context provider)
  • restart Continue extension
  • check Continue’s output panel for errors
JetBrains-specific issues?
  • ensure Continue plugin is up to date
  • check IDE version is compatible
  • try invalidating caches and restarting
slow responses?
  • reduce the time range you’re querying
  • be more specific with filters
  • avoid requesting screenshots unless needed
still stuck? ask in our discord — we can help troubleshoot.

​
resources