google-ai-mode-mcp

70/100

Capped at 70: core tools not tested (only setup or self-check calls passed); the tests add up to 100. Why scores are capped

Last tested 2026-11-09 (Fresh: tested within 30 days) Connects · tools listedNo tool call tested yet No key to connect

No advisories in range for tested dbd42638a50b65e7fa3f571aca0bd1229ec6f891 (checked 2026-11-10)

Security review: not tested

Test points add up to 100; the score is capped at 70 until a tool call passes. Not a quality or security rating. Methodology

Test points before the cap (100/100)

  • Install20/20
  • Handshake30/30
  • Maintenance25/25
  • Docs15/15
  • License10/10

Git-only (pinned)
Git-only (pinned): installed from GitHub commit dbd42638a50b65e7fa3f571aca0bd1229ec6f891 (uvx --from git+https://github.com/timoncool/google-ai-mode-mcp@<sha>#subdirectory=server google-ai-mode-mcp), build run only inside our no-network sandbox. Initialize and tools/list worked (5 tools). Installed from the repo's server/ subdirectory (uvx --from git+…@<sha>#subdirectory=server; hatchling build, no install scripts). Real call (no credentials): health returned status ok with extension_connected false. search, search_many, follow_up and generate_image were not called: they need the project's Chrome/Firefox extension in a browser signed in to Google. On start the server launches a separate local HTTP backend (127.0.0.1:15551) that kept running after our MCP session closed; we stopped it by hand. npm google-ai-mode-mcp is an unrelated older package by another author. Not listed on Glama when tested. Score capped at 70 (setup and self-check calls do not count as a tested tool): only the health self-check passed; core tools not tested (search needs the browser extension and a Google sign-in).
Tool-call test (2026-11-09, direct MCP stdio client, no LLM): self-check only. 1 of 1 call passed (health self-check). Search tools not called (need the browser extension and a Google sign-in). Setup/self-check calls only: core tools not tested. Evidence: local test run, Nov 9, 2026.

Transport (tested 2026-11-09): stdio

Tested version: 0.3.0 (commit dbd4263) · tested 2026-11-09

Token cost (estimate): approx. 786 tokens, cl100k estimate (5 tools, measured 2026-11-11, SHA dbd42638a50b65e7fa3f571aca0bd1229ec6f891). This is an estimate from our testing of the tool names, descriptions and input schemas, counted with cl100k_base.

Permissions: 2 read, 0 write (state-changing), 3 unclassified · Auth: none · Rate limit: unknown · Pricing unit: unknown

Auth: none. Rate limit: unknown. Pricing unit: unknown.

  • follow_up — unclassified
  • generate_image — unclassified
  • health — unclassified
  • search — read
  • search_many — read

handshake and tools listed without a recorded key or OAuth

Score 70/100 · Tools 5 · Token cost approx. 786 tokens · Compare · Last tested 2026-11-09 · Version tested dbd42638a50b65e7fa3f571aca0bd1229ec6f891 · Package google-ai-mode-mcp · Repo timoncool/google-ai-mode-mcp

Summary: google-ai-mode-mcp completed an MCP handshake without credentials and exposed 5 tools.

Evidence summary

Handshake
pass
Tools listed
5
Context cost
approx. 786 tokens, cl100k estimate (5 tools, measured 2026-11-11, SHA dbd42638a50b65e7fa3f571aca0bd1229ec6f891; an estimate) ranking · add up your servers' context cost
API key
No key to connect (handshake passed)
Tested
2026-11-09

Test results

TestResultPointsEvidence
installpass20uvx --from git+https://github.com/timoncool/google-ai-mode-mcp@dbd42638a50b65e7fa3f571aca0bd1229ec6f891#subdirectory=server google-ai-mode-mcp (git install pinned to commit dbd42638a50b65e7fa3f571aca0bd1229ec6f891, Node 20 / Python venv, Linux, scrubbed env) succeeded in 2s; installed package resolves to the pinned SHA (google-ai-mode-mcp @ git+https://github.com/timoncool/google-ai-mode-mcp@dbd42638a50b65e7fa3f571aca0bd1229ec6f891#subdirectory=server).
handshakepass30MCP initialize + tools/list over stdio succeeded with no credentials; 5 tools listed in 1.8s.
maintenancepass25Pinned commit dbd4263 dated 2026-11-09 (https://api.github.com/repos/timoncool/google-ai-mode-mcp/commits/dbd42638a50b65e7fa3f571aca0bd1229ec6f891), 0 days before test; 16 GitHub stars.
docspass15README over 3,000 chars; install instructions present; mcpServers config example present. Check of the package's own README (README.md at pinned commit dbd4263 (raw.githubusercontent.com)).
licensepass10MIT (OSI-approved).

Local-model readiness

Token cost (estimate): approx. 786 tokens, cl100k estimate for 5 tools · about 10% of an 8k context. This is an estimate from our testing (counted with cl100k_base).

Small-model friendly (schema heuristic, not a model result): unknown.

Not tested

Small-model task runs: Not yet tested.

What we tested and what we didn't

Tested on 2026-11-09

  • Install from the registry
  • We connected with no credentials and asked for its tool list: it listed 5 tools (Method details: MCP initialize then tools/list)
  • Maintenance signals (last push, archived/deprecated status)
  • Docs (README length, install and config example)
  • License (OSI-approved or not)
  • Token cost (estimate)

Not tested

  • Security: not audited (no code review, no permission or data-flow analysis)
  • Real tasks (no functional task runs yet)
  • Behaviour with real credentials or a real account
  • Performance, rate limits or load
  • Correctness of results beyond the listed tasks

Methodology: how we test. A high score means it installs and responds, not that giving it access to your data carries no risk.

Known security issues

Checked on 2026-11-10 for version dbd42638a50b65e7fa3f571aca0bd1229ec6f891 against GitHub repository advisories. Scope: the package itself; dependencies not scanned.

No published advisories found in OSV and GitHub advisories for github.com/timoncool/google-ai-mode-mcp dbd42638a50b65e7fa3f571aca0bd1229ec6f891 as of 2026-11-10. This is not a security audit.

Monthly roundup: MCP security issues, October 2026.

Tool list changes

Unchanged since the previous snapshot (latest 2026-11-11).

Snapshot hash (fingerprint of the tool list)

06a4232f24da: SHA-256 of the canonical tool names, descriptions and input schemas. If it changes, the tool list changed.

Feeds: RSS · JSON.

Raw test record (JSON)
{
  "name": "google-ai-mode-mcp",
  "version": "dbd42638a50b65e7fa3f571aca0bd1229ec6f891",
  "registry": "git",
  "status": "working",
  "tested": "2026-11-09",
  "tools_count": 5,
  "deprecated": false,
  "archived": false,
  "tests": {
    "install": [
      "pass",
      20,
      "`uvx --from git+https://github.com/timoncool/google-ai-mode-mcp@dbd42638a50b65e7fa3f571aca0bd1229ec6f891#subdirectory=server google-ai-mode-mcp` (git install pinned to commit dbd42638a50b65e7fa3f571aca0bd1229ec6f891, Node 20 / Python venv, Linux, scrubbed env) succeeded in 2s; installed package resolves to the pinned SHA (google-ai-mode-mcp @ git+https://github.com/timoncool/google-ai-mode-mcp@dbd42638a50b65e7fa3f571aca0bd1229ec6f891#subdirectory=server)."
    ],
    "handshake": [
      "pass",
      30,
      "MCP `initialize` + `tools/list` over stdio succeeded with no credentials; 5 tools listed in 1.8s."
    ],
    "maintenance": [
      "pass",
      25,
      "Pinned commit dbd4263 dated 2026-11-09 (https://api.github.com/repos/timoncool/google-ai-mode-mcp/commits/dbd42638a50b65e7fa3f571aca0bd1229ec6f891), 0 days before test; 16 GitHub stars."
    ],
    "docs": [
      "pass",
      15,
      "README over 3,000 chars; install instructions present; `mcpServers` config example present. Check of the package's own README (README.md at pinned commit dbd4263 (raw.githubusercontent.com))."
    ],
    "license": [
      "pass",
      10,
      "MIT (OSI-approved)."
    ]
  }
}

Install

uvx --from git+https://github.com/timoncool/google-ai-mode-mcp@dbd42638a50b65e7fa3f571aca0bd1229ec6f891#subdirectory=server google-ai-mode-mcp

Tools listed

follow_up, generate_image, health, search, search_many

Tool history: captured Nov 11, 2026. All tool history.

Quick config

{
  "mcpServers": {
    "google-ai-mode-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/timoncool/google-ai-mode-mcp@dbd42638a50b65e7fa3f571aca0bd1229ec6f891#subdirectory=server",
        "google-ai-mode-mcp"
      ]
    }
  }
}

Add to config Opens the config generator with this server selected.

Setup

  1. Install. Run uvx --from git+https://github.com/timoncool/google-ai-mode-mcp@dbd42638a50b65e7fa3f571aca0bd1229ec6f891#subdirectory=server google-ai-mode-mcp (git install pinned to commit dbd42638a50b65e7fa3f571aca0bd1229ec6f891). This is the exact command we ran on 2026-11-09.
  2. Configure. Add the mcpServers entry below to your MCP client config.
  3. Verify. Restart the client and check that tools/list returns tools (5 in our test).
{
  "mcpServers": {
    "google-ai-mode-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/timoncool/google-ai-mode-mcp@dbd42638a50b65e7fa3f571aca0bd1229ec6f891#subdirectory=server",
        "google-ai-mode-mcp"
      ]
    }
  }
}

Test history

Follow this server (RSS) · Monthly changelog

FAQ

Is google-ai-mode-mcp deprecated?

No. google-ai-mode-mcp was not deprecated or archived when we last tested it on 2026-11-09.

What replaces google-ai-mode-mcp?

Nothing; google-ai-mode-mcp is not deprecated as of 2026-11-09.

Does google-ai-mode-mcp need an API key?

No. It completed an MCP handshake with no credentials and listed 5 tools.

Embed the badge

TestedMCP: 70/100, tested 2026-11-09

Every tested server gets a free embeddable badge. It shows the current score and test date and expires after 90 days. Testing is free; payment never changes a score.

Claim this listing · Report an issue