A lightweight Linear MCP server for Claude Code that exposes one tool with action dispatch (search, get, update, comment, create, graphql, help) using ~500 tokens instead of the standard MCP's ~17,000.
MCPpedia last refreshed this data
Streamlinear is an MCP server that a lightweight Linear MCP server for Claude Code that exposes one tool with action dispatch (search, get, update, comment, create, graphql, help) using ~500 tokens instead of the standard MCP's ~17,000. Its tool list has not been published yet over stdio, requires no API key, and scores 57/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients - only the file and path differ.
{
"mcpServers": {
"linear-work": {
"env": {
"LINEAR_API_TOKEN": "${LINEAR_WORK_TOKEN}"
},
"args": [
"-y",
"@primeradianthq/streamlinear@1.1.3"
],
"command": "npx",
"envFrom": [
"LINEAR_WORK_TOKEN"
]
},
"linear-personal": {
"env": {
"LINEAR_API_TOKEN": "${LINEAR_PERSONAL_TOKEN}"
},
"args": [
"-y",
"@primeradianthq/streamlinear@1.1.3"
],
"command": "npx",
"envFrom": [
"LINEAR_PERSONAL_TOKEN"
]
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
A lightweight Linear MCP for Claude Code. One tool, seven actions.
Run this in your terminal to verify the server starts. Then let us know if it worked - your result helps other developers.
npx -y 'streamlinear-cli' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories - click any category to see the underlying evidence.
No known CVEs.
Checked streamlinear-cli against OSV.dev.
Be the first to review
Have you used this server?
Share your experience - it helps other developers decide.
Sign in to write a review.
Others in ai-ml
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
An open-source AI agent that brings the power of Gemini directly into your terminal.
🛡️ BLA (Blind LLM Agents) — Adversarial defense shield that protects binaries, Electron apps, JS bundles, Python, and WebAssembly against AI reverse-engineering agents like REA. Poison -> Exhaust -> Hallucinate.
Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
MCP Security Weekly
Get CVE alerts and security updates for Streamlinear and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
A lightweight Linear MCP for Claude Code. One tool, seven actions.
The standard Linear MCP uses ~17,000 tokens for tool definitions.
streamlinear uses ~500 tokens.
Instead of 23 separate tools, streamlinear has one tool with action dispatch:
{"action": "search"}
{"action": "get", "id": "ABC-123"}
{"action": "update", "id": "ABC-123", "state": "Done"}
{"action": "comment", "id": "ABC-123", "body": "Fixed!"}
{"action": "create", "title": "New bug", "team": "ENG"}
{"action": "graphql", "graphql": "query { viewer { name } }"}
{"action": "help"}
| Action | Purpose |
|---|---|
search | Find issues (smart defaults: your active issues) |
get | Issue details by ABC-123, URL, or UUID |
update | Change state, priority, assignee |
comment | Add comment to issue |
create | Create new issue |
graphql | Raw GraphQL for anything else |
help | Full documentation |
Add to your .mcp.json:
{
"mcpServers": {
"linear": {
"command": "npx",
"args": ["-y", "@primeradianthq/streamlinear@1.2.1"],
"env": {
"LINEAR_API_TOKEN": "lin_api_xxxxx"
}
}
}
}
To use streamlinear with multiple Linear workspaces, create separate MCP entries and map each secret to LINEAR_API_TOKEN:
{
"mcpServers": {
"linear-personal": {
"command": "npx",
"args": ["-y", "@primeradianthq/streamlinear@1.2.1"],
"env": {
"LINEAR_API_TOKEN": "${LINEAR_PERSONAL_TOKEN}"
},
"envFrom": ["LINEAR_PERSONAL_TOKEN"]
},
"linear-work": {
"command": "npx",
"args": ["-y", "@primeradianthq/streamlinear@1.2.1"],
"env": {
"LINEAR_API_TOKEN": "${LINEAR_WORK_TOKEN}"
},
"envFrom": ["LINEAR_WORK_TOKEN"]
}
}
}
When installed as a dependency, the package provides two binaries:
npm install @primeradianthq/streamlinear@1.2.1
npx streamlinear-cli help
npx streamlinear
The MCP server requires LINEAR_API_TOKEN at runtime. Consumers such as Scribble may expose their own operator-facing variable and map it to LINEAR_API_TOKEN before starting streamlinear.
Set STREAMLINEAR_POST_ONLY=1 when confidentiality requires that the agent never read issue content. The server then refuses the read actions (search, get, and graphql) while create, update, comment, and help keep working. Internal lookups such as team names and workflow states still happen; they expose workspace metadata, not issue content.
search with no params → your assigned issues, not completed/canceledassignee: "me" uses the authenticated user@name in create descriptions and comment bodies becomes a Linear profile link when it matches exactly one workspace userFor anything not covered by the main actions, use raw GraphQL:
{
"action": "graphql",
"graphql": "query { projects { nodes { id name } } }"
}
Use {"action": "help"} for common GraphQL patterns.
MIT