Field-by-field comparison

Compare the evidence before choosing an MCP.

Each signal stays separate, missing facts remain visible, and the column order follows your selection.

MCPs in this comparison

Uncheck an MCP to remove it. Comparing two or three keeps each signal in its own row.

Open canonical comparison link

Comparable alternatives

Shown only when capability or industry context overlaps.

Side-by-side MCP evidence comparison
Evidence fieldLinear MCPMCP100 SelectedWindows-MCPMCP100 Selected
Task fit
Best for
  • Searching and summarizing Linear issues and projects
  • Human-supervised issue, project, and comment updates
  • Read-only planning assistants using Linear's dedicated read-only endpoint
  • Using an AI client to inspect and operate Windows applications when no safer application API exists
Not ideal for
  • Fully autonomous project administration
  • Organizations that cannot authorize third-party MCP clients
  • Workflows requiring Linear capabilities not exposed by the current MCP tools
  • Deterministic automation that can be implemented through a documented API, CLI, or test framework
Avoid when
  • The client cannot securely complete OAuth or protect bearer credentials
  • Issue and roadmap content cannot be shown to the selected AI client or model
  • Write operations cannot be independently reviewed or audited
  • The desktop session contains sensitive applications, credentials, messages, or files outside the task
Provenance
Provenance details

First-party MCP

Linear · Publisher source ↗

Community implementation

io.github.CursorTouch · Publisher source ↗

Maintenance
Maintenance details

Repo: Not documented

Package: Not documented

Repo: Aug 14, 2026

Package: Aug 1, 2026

Popularity evidence
GitHub starsNot documented

6,749

GitHub stars · checked 2026-08-14T18:46:26.000Z

30-day package downloadsNo reliable download data

40,449

PyPI Stats package downloads · checked 2026-08-14T18:46:26.000Z

External adoption evidenceNot documented
  • github: repository stars: 6,749Exact attributable signal.github: repository stars · Admission snapshot · checked 2026-08-14T18:46:26.000ZEvidence source ↗
  • PyPI Stats: package downloads: 40,449Non-comparable contextual signal.PyPI Stats: package downloads · Provider last month · checked 2026-08-14T18:46:26.000ZEvidence source ↗
Client coverage
Client coverage details
Claude Code✓ Streamable HTTP
Claude Desktop✓ Streamable HTTP
Codex✓ Streamable HTTP
VS Code✓ Streamable HTTP
Cursor✓ Streamable HTTP
OpenCode✓ Streamable HTTP
Claude Code✓ Local stdio
Claude Desktop✓ Local stdio
Codex✓ Local stdio
VS Code✓ Local stdio
Cursor✓ Local stdio
OpenCode✓ Local stdio
Client coverage noteLocal stdio runs on your computer. Streamable HTTP connects to a remotely hosted MCP server.
Access and data
AuthenticationOAuth 2.1 with dynamic client registration is the primary method. Linear also documents bearer tokens and scoped API keys.Stdio has no network listener. Non-loopback HTTP requires an auth key or OAuth unless insecure access is explicitly allowed; IP allowlists, TLS, CORS, and host validation are documented.
CostLinear documents no separate MCP server fee on its setup page. A Linear account is required, and normal plan capabilities, limits, and charges still apply.The MIT-licensed project lists no MCP fee. Windows, Python, hosting, client, and model costs are separate.
PermissionsThe standard endpoint exposes read and write tools for issues, projects, comments, and related Linear objects under the user's permissions. https://mcp.linear.app/mcp/readonly exposes only read tools, and Linear also documents read-only API keys.Runs with the invoking user's full Windows permissions, including PowerShell, files, registry, processes, UI input, screenshots, and web scraping; many actions are irreversible.
Data handlingAuthorized Linear issue, project, comment, and related workspace data is retrieved by Linear's hosted server and returned to the MCP client. Write calls can change workspace records.Processing is local. Telemetry excludes screenshots, state captures, arguments, and outputs but includes status, duration, tool and client information, anonymized sessions, and possibly paths in error messages.
Limitations
Tradeoffs
  • Hosted operation removes local server maintenance but places Linear workspace data in the connected AI workflow.
  • The standard endpoint is read-write; the dedicated read-only endpoint materially reduces integrity risk.
  • API keys enable non-interactive use but shift secret storage, scoping, and rotation duties to the operator.
  • General computer-use reaches many applications, but visual automation is brittle and broad input control can produce high-impact unintended actions.
Risk contextInternal roadmap and issue data can be disclosed, and the default endpoint can modify collaboration records. Prefer the read-only endpoint for research, use least-privilege credentials, and require approval for mutations.It is not sandboxed and can delete files, alter registry or system settings, type into applications, and execute PowerShell. Use a VM or low-privilege account, backups, supervision, loopback binding, and disabled high-risk tools.
Evidence date
Editorial review2026-07-242026-08-11
Candidate evidence2026-07-29T20:58:26.000Z2026-08-14T18:46:26.000Z

Popularity, maintenance, fit, permissions, and client support are independent evidence fields.

Read the evidence method →