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 fieldPerplexity MCPWatchlist candidateExa MCPMCP100 Selected
Task fit
Best for
  • Connect compatible AI clients to Perplexity's documented MCP capabilities.
  • Search the web, retrieve pages, find code, and run research workflows through Exa.
  • Teams already using Exa that can test with non-sensitive data and least privilege.
Not ideal for
  • Users who need a fully reviewed MCP100 recommendation today
  • Users who need an MCP100-selected recommendation today
  • Unattended production workflows before permissions and failure behavior are reviewed
Avoid when
  • Permissions, credentials, and connected data cannot be tested with least privilege
  • The connected data or account cannot be safely exposed to the selected AI client
  • You cannot verify least-privilege access and review write-capable tool calls
Provenance
Provenance details

First-party MCP

Perplexity · Publisher source ↗

First-party MCP

Exa · Publisher source ↗

Maintenance
Maintenance details

Repo: Jul 30, 2026

Package: Jul 27, 2026

Repo: Aug 10, 2026

Package: Aug 1, 2026

Popularity evidence
GitHub stars

2,442

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

4,867

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

30-day package downloads

93,274

30-day package downloads · checked 2026-07-29T17:30:00.000Z

87,547

30-day package downloads · checked 2026-08-14T18:46:26.000Z

External adoption evidence
  • zPlatform: Weekly downloads: 19,692zPlatform: Weekly downloads · Weekly · checked 2026-07-20T08:05:31.779ZEvidence source ↗
  • npm: package downloads: 93,274Exact attributable signal.npm: package downloads · Admission snapshot · checked 2026-07-29T17:30:00.000ZEvidence source ↗
  • github: repository stars: 2,442Exact attributable signal.github: repository stars · Admission snapshot · checked 2026-08-14T18:46:26.000ZEvidence source ↗
  • github: repository stars: 4,867Exact attributable signal.github: repository stars · Admission snapshot · checked 2026-08-14T18:46:26.000ZEvidence source ↗
Client coverage
Client coverage details
Claude Code✓ Local stdio
Claude Desktop✓ Local stdio
Codex✓ Local stdio
VS Code✓ Local stdio
Cursor✓ Local stdio
OpenCode✓ Local stdio
Claude Code✓ Streamable HTTP
Claude Desktop✓ Streamable HTTP
Codex✓ Streamable HTTP
VS Code✓ Streamable HTTP
Cursor✓ Streamable HTTP
OpenCode✓ Streamable HTTP
Client coverage noteLocal stdio runs on your computer. Streamable HTTP connects to a remotely hosted MCP server.
Access and data
AuthenticationFollow only the publisher source; credential storage, scopes, and revocation remain under review.Authentication follows the publisher's documented endpoint or local-server configuration. OAuth scopes, API-key handling, and revocation behavior remain review items.
CostPublisher plans, API usage, infrastructure, or per-action charges may apply; MCP100 has not published a cost conclusion.No MCP100 cost conclusion is published yet. The publisher's account plan, API usage, infrastructure, or per-action charges may apply.
PermissionsExact permissions and read/write boundaries have not completed MCP100 review.Exact permissions and the read/write boundary have not yet completed MCP100 independent review; consult the linked publisher sources and use the narrowest available scope.
Data handlingCandidate-specific retention, subprocess, telemetry, and model-data behavior remain review items.Publisher-accessible account or application data may be returned to the MCP client and its selected model. Retention and subprocess behavior require candidate-specific review.
Limitations
Tradeoffs
  • Publisher attribution supports discovery, but does not replace an independent permissions and usability review.
  • First-party provenance and a clear task improve confidence, but do not replace an independent permissions and usability review.
  • Client transport compatibility does not prove that authentication, scopes, failure handling, and every tool behave safely.
Risk contextUse a test account, least privilege, read-only controls where available, and explicit approval for mutations.Use a test workspace or non-production account, least privilege, read-only controls where available, explicit approval for mutations, and credential revocation after evaluation.
Evidence date
Editorial review2026-07-242026-07-24
Candidate evidence2026-08-14T18:46:26.000Z2026-08-14T18:46:26.000Z

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

Read the evidence method →