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 fieldGoogle Cloud Firestore MCPShortlist candidateRedis MCPMCP100 Recommended
Task fit
Best for
  • Firestore document inspection and project database operations
  • Use for Firestore-backed app debugging and data workflows.
  • Inspecting and manipulating Redis strings, hashes, lists, sets, sorted sets, streams, JSON, and search indexes
  • Development workflows using a dedicated local or test Redis database
  • Redis documentation search and operational investigation
Not ideal for
  • Official API exposes create, update and delete and database creation tools.
  • Read-only analytics when write-capable Redis tools cannot be disabled or constrained by ACL
  • Production databases shared with latency-sensitive applications
Avoid when
  • Official API exposes create, update and delete and database creation tools.
  • The Redis credential grants unrestricted access to production keys
  • TLS certificate verification is disabled for a remote Redis connection
  • The agent must not read, overwrite, publish, expire, or delete Redis data
Provenance
Provenance details

First-party MCP

Google · Publisher source ↗

First-party MCP

Redis · Publisher source ↗

Maintenance
Maintenance details

Repo: Not documented

Package: Not documented

Repo: Sep 21, 2026

Package: Not documented

Popularity evidence
GitHub starsNot documented

628

GitHub stars · checked 2026-09-24T04:14:26.347000Z

Client coverage
Client coverage detailsNot documented
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
AuthenticationGoogle and Google Cloud remote MCP servers support user credentials or dedicated application credentials. OAuth 2.0 and IAM-principal based authentication are documented; Google Cloud MCP calls require MCP Tool User permission plus resource-specific IAM permissions.Supports Redis username/password URLs, individual credential options, TLS through `rediss://`, CA certificate verification, cluster mode, and Microsoft Entra ID authentication for Azure Managed Redis.
CostFirestore can charge for document reads/writes/deletes, index-entry reads, storage, bandwidth, backups/PITR and other operations. Free quota exists for some usage, but several features require billing.The first-party server is open source and the PyPI package documents no MCP usage fee. Redis Cloud, infrastructure, network, container, and AI-client costs remain separate.
PermissionsEffective access is controlled by Google Cloud IAM. The Firestore MCP exposes both read and write/admin tools, including add/update/delete document, create/update/delete database, index operations, and backup/schedule operations.The server can read and write Redis keys and data structures, operate streams and pub/sub, manage search indexes, and inspect server information according to the connected Redis user's ACL. Redis ACL configuration is the effective permission boundary.
Data handlingNot documented in the reviewed sources. The Firestore MCP reference does not make a separate MCP-specific retention or training claim; requests operate on Firestore resources under the authenticated Google Cloud identity.The stdio server runs locally and sends Redis query inputs and returned key values to the connected MCP client. It connects directly to the configured Redis deployment. Credentials can be supplied in a URI, CLI arguments, or environment variables; avoid embedding them in shareable config and logs.
Limitations
Tradeoffs
  • API enablement/billing/scopes and remaining tools require check
  • The server supports a wide Redis data surface, which is useful but makes the database credential the primary security boundary.
  • Running through uvx is simple but `@latest` is mutable; pin a reviewed release for repeatable deployments.
  • Connection URLs are convenient but can expose usernames and passwords in process arguments or client configuration.
Risk contextThis is a write-capable database/admin MCP. Incorrect tool calls can change or delete documents, databases, indexes, backups, or schedules and can generate billable usage.A broad Redis tool set can expose or mutate application state, sessions, queues, cached records, and vector data. Use a dedicated database, a narrowly scoped ACL user, verified TLS, pinned releases, and backups. This review does not claim MCP100 execution testing.
Evidence date
Editorial review2026-10-192026-07-24
Candidate evidence2026-10-192026-09-24T04:25:05.554391Z

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

Read the evidence method →