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 fieldAtlassian Remote MCPMCP100 SelectedKiCAD MCP ServerMCP100 Selected
Task fit
Best for
  • Searching and summarizing Jira and Confluence knowledge
  • Creating and updating Jira work items or Confluence content with approval
  • Connecting supported AI clients to Atlassian Cloud without self-hosting a server
  • Assisting with KiCad project inspection and repetitive PCB or schematic editing tasks
Not ideal for
  • Atlassian Server or Data Center deployments
  • Organizations that do not allow enterprise content to pass through an external AI client
  • Headless use when organization administrators do not permit API-token authentication
  • Safety-critical electrical design or final design-rule approval without an experienced engineer
Avoid when
  • The AI client is not approved for the Jira, Confluence, Bitbucket, Compass, or connected third-party data involved
  • Existing Atlassian user permissions are too broad for agent use
  • Write and bulk actions cannot require review
  • You cannot version, inspect, and independently validate every generated design change
Provenance
Provenance details

First-party MCP

Atlassian · Publisher source ↗

Community implementation

github:mixelpixx · Publisher source ↗

Maintenance
Maintenance details

Repo: Not documented

Package: Not documented

Repo: Aug 14, 2026

Package: Not documented

Popularity evidence
GitHub starsNot documented

1,876

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

External adoption evidenceNot documented
  • github: repository stars: 1,876Exact attributable signal.github: repository stars · Admission snapshot · 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 browser authorization is the default and recommended method. Admin-enabled, scoped personal API tokens support headless use and are required for Jira Service Management and Bitbucket Cloud tools; Compass tools require OAuth.No authentication is documented for the local MCP server. JLCPCB live lookup optionally uses JLCPCB_APP_ID, JLCPCB_API_KEY, and JLCPCB_API_SECRET; local catalog search needs no credentials.
CostThe core connection has no separately stated MCP fee. Users need applicable Atlassian Cloud products and an AI client. Beta tools are currently free; Atlassian says some may later be billed in Rovo credits with notice, and Teamwork Graph calls are expected to consume credits at general availability.The MIT-licensed server lists no MCP fee. The JLCPCB guide says Basic parts have free assembly and Extended parts charge a $3 setup fee per unique part; manufacturing charges are separate.
PermissionsTools are grouped by product and read, write, or search intent. Organization admins grant or revoke permission groups, and calls also honor the connected user's Jira, Confluence, Jira Service Management, Bitbucket, Compass, project, space, IP-allowlist, and OAuth or API-token scopes.Reads and writes KiCad boards, schematics, projects, libraries, and assets, with auto-save, UI control, autorouting, exports, and optional JLCPCB catalog and API operations.
Data handlingThe Atlassian-hosted server retrieves and returns authorized Atlassian Cloud content to the external MCP client. Teamwork Graph tools can aggregate relationships across Atlassian products and connected third-party apps and may use AI processing. Traffic uses HTTPS/TLS, and Atlassian records tool-use events in the organization audit log.Local operations read and write design files and paths. Developer logs contain tool-call history, paths, and design details. Optional JLCPCB lookups send configured credentials and requests to JLCPCB; retention is not documented.
Limitations
Tradeoffs
  • The hosted service honors existing product permissions and provides audit events, but it can expose broad enterprise knowledge to the connected AI client.
  • OAuth 2.1 is recommended; API tokens support headless workflows but require admin enablement and careful scope management.
  • Some Teamwork Graph and search tools are Beta and may later consume paid Rovo credits.
  • Automation can accelerate layout work, but malformed or electrically incorrect edits may look plausible and can become expensive after fabrication.
Risk contextThe integration can read and modify enterprise work and knowledge across several Atlassian products. Approve client domains, use least privilege, restrict permission groups and token scopes, retain write confirmation, review audit logs, and evaluate the external AI client's data policy. This review does not claim MCP100 execution testing.Auto-save, deletion, board and schematic writes, routing, and external integrations can damage designs or expose files and credentials. Use backups and version control, review writes, and protect environment files and logs.
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 →
Compare MCPs | MCP100 Index