# Grok Build (npm · grok-build-mcp-server)

Run the Grok Build CLI as MCP tools: agent runs with live progress, code review, web research.

- Trust score: 91/100 (high trust)
- Change this week: −1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- npm · `grok-build-mcp-server`: 91/100 (this document), [markdown](https://verifymcp.io/servers/nuruvala-grok-build-mcp-server/grok-build-mcp-server.md), [page](https://verifymcp.io/servers/nuruvala-grok-build-mcp-server/grok-build-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `grok-build-mcp-server`
- Version: `0.2.5`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 95 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Nuruvala/grok-build-to-claude).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 31 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2298 tokens (~287/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 83/100
  - Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Grok Build MCP server?

Grok Build runs locally as an npm package, launched with npx -y grok-build-mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add nuruvala-grok-build-mcp-server -- npx -y grok-build-mcp-server
```

### Cursor

```json
{
  "mcpServers": {
    "nuruvala-grok-build-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "grok-build-mcp-server"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "nuruvala-grok-build-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "grok-build-mcp-server"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add nuruvala-grok-build-mcp-server -- npx -y grok-build-mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "nuruvala-grok-build-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "grok-build-mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add nuruvala-grok-build-mcp-server --command npx --arg -y --arg grok-build-mcp-server
```

### Hermes

```yaml
mcp_servers:
  nuruvala-grok-build-mcp-server:
    command: "npx"
    args: ["-y", "grok-build-mcp-server"]
```

### Netclaw

```json
{
  "McpServers": {
    "nuruvala-grok-build-mcp-server": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "grok-build-mcp-server"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add nuruvala-grok-build-mcp-server -t stdio -c npx -a -y grok-build-mcp-server
```

### Other

```json
{
  "mcpServers": {
    "nuruvala-grok-build-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "grok-build-mcp-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-21 (score 91, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-20 (score 90, −3)

- [functional] Stability: pass → 0.80

### 2026-09-19 (score 93, 0)

- [security] Stability: 0.97 → pass

### 2026-09-18 (score 93, 0)

- [functional] Stability: pass → 0.97

### 2026-09-17 (score 93, 0)

- [security] Stability: 0.97 → pass

### 2026-09-16 (score 93, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 92, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 91, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (8)

### `check` (~54 tokens)

Check Grok Build readiness

Report grok-build-mcp-server status: version, resolved grok binary, permission ceiling, CLI readiness (`grok version`, `grok models`), and run defaults. Call this first when a grok tool behaves unexpectedly.

### `grok` (~806 tokens)

Run Grok Build

Run a headless Grok Build agent (`grok -p`). Returns the model text plus session, usage, and cost metadata. Permission is capped by GROK_MCP_PERMISSION_CEILING; requests above it are rejected rather than silently downgraded.

Input parameters:

- `agent` (string): Named subagent to run, passed as `--agent`.
- `allow` (array): Repeatable allow rules in `ToolPrefix(glob)` form, e.g. `Bash(npm*)`, `Write(src/**)`.
- `background` (boolean): Run detached and return a runId immediately instead of waiting. Poll with the `status` tool. The run survives a restart of this MCP server. `false` is not a request.
- `continueSession` (boolean): Continue the most recent session for `cwd` (`--continue`). Mutually exclusive with `resume`. `false` is not a request.
- `cwd` (string): Absolute path. Working directory for the run. Passed as `--cwd`. Use the narrowest useful path. Under `permission: "write"` this is also the sandbox root: the run cannot write outside it, and a refus…
- `deny` (array): Repeatable deny rules in `ToolPrefix(glob)` form, e.g. `Read(.env)`.
- `disableWebSearch` (boolean): Pass `--disable-web-search`. `false` is not a request.
- `disallowedTools` (array): Internal tool ids to block, passed as `--disallowed-tools`.
- `effort` (string): Reasoning effort passed as `--effort`. Omit to use the server default. Values are passed through; the CLI rejects what the model does not advertise.
- `forkSession` (string): UUID for a forked session. Requires `resume` or `continueSession`. Passed as `--fork-session --session-id`.
- `maxTurns` (integer): Maximum agentic turns. Passed as `--max-turns`. Headless only.
- `model` (string): Model id to pass as `--model`. Omit to use the server default. Unknown ids are rejected by the CLI, not by this server.
- `permission` (string): Permission level for this run: `read-only` (plan mode, read-only sandbox), `write` (accepts edits, sandboxed to `cwd`), or `full` (no sandbox). Must be at or below GROK_MCP_PERMISSION_CEILING. Omit t…
- `prompt` (string, required): The task for Grok to perform. Passed verbatim as `grok -p`.
- `resume` (string): Resume an existing session by id or title (`--resume`). Mutually exclusive with `continueSession`. Combine with `forkSession` to fork rather than continue in place.
- `rules` (string): Extra system-prompt text, passed as `--rules`. Longer system-prompt text belongs in the prompt.
- `sessionId` (string): Create a NEW session with this UUID (`--session-id`). Cannot be combined with `resume` or `continueSession`; use `forkSession` to name a fork.
- `tools` (array): Internal tool ids to allow, passed as a single comma-joined `--tools`. Shell is `run_terminal_command`, not `bash`.
- `write` (boolean): Shorthand for `permission: "write"`. Ignored when `permission` is set. `false` is not a request.
- `yolo` (boolean): Shorthand for `permission: "full"`. Ignored when `permission` is set. `false` is not a request.

### `review` (~455 tokens)

Review a git diff

Review a git diff with Grok Build. Targets the working tree (`uncommitted`), a merge-base diff against `base`, or a single `commit`. When none is specified, auto-detects: the upstream diff if the branch is ahead, otherwise the working tree. Always runs read-only (`--permission-mode plan --sandbox read-only`) regardless of GROK_MCP_PERMISSION_CEILING — this tool has no permission, write, or yolo argument, because a review that edits the code it is reviewing is never wanted. Set `structured: true` for machine-readable findings.

Input parameters:

- `background` (boolean): Run detached and return a runId immediately instead of waiting. Poll with the `status` tool. The run survives a restart of this MCP server. `false` is not a request.
- `base` (string): Review the merge-base diff against this ref. Mutually exclusive with commit and uncommitted.
- `commit` (string): Review this commit. Mutually exclusive with base and uncommitted.
- `cwd` (string): Absolute path. Repository to review. Defaults to the current working directory.
- `effort` (string): Reasoning effort passed as `--effort`. Omit to use the server default. Values are passed through; the CLI rejects what the model does not advertise.
- `instructions` (string): Extra reviewer guidance, appended verbatim to the prompt.
- `maxTurns` (integer): Maximum agentic turns. Passed as `--max-turns`. Headless only.
- `model` (string): Model id to pass as `--model`. Omit to use the server default. Unknown ids are rejected by the CLI, not by this server.
- `structured` (boolean): Return machine-readable findings via `--json-schema`. A run that stops before a final findings object fails the call with reviewIncomplete. Malformed model JSON after a normal stop degrades to raw te…
- `uncommitted` (boolean): Review the working tree (staged, unstaged, and untracked). Mutually exclusive with base and commit. `false` is not a request.

### `sessions` (~238 tokens)

List Grok sessions

List and search Grok Build sessions from the local store ($GROK_HOME/sessions). Search is local-only: it does not consult `grok sessions search` or any remote index. Pass `id` for a single session, `query` for a case-insensitive substring over title, first prompt, and id, and `cwd` to keep only sessions that started in that directory. A reported id resumes from any directory with `grok -r <id>` or the grok tool's `resume` argument.

Input parameters:

- `cwd` (string): Keep only sessions that *started* in this directory. Resume still works from anywhere (`grok -r <id>`).
- `id` (string): Exact session id lookup. Ignores query, cwd, and limit. Falls back to a case-insensitive match.
- `limit` (integer): Maximum rows to return. Default 20. Ignored when `id` is set.
- `query` (string): Case-insensitive substring over title, first prompt, and id. Search is local-only: it does not consult `grok sessions search` or any remote index.

### `websearch` (~402 tokens)

Search the web with Grok Build

Research a question with Grok Build's web search. `numResults` and `searchDepth` shape the prompt only — the CLI has no flags for either. Always runs read-only (`--permission-mode plan --sandbox read-only`) regardless of GROK_MCP_PERMISSION_CEILING — this tool has no permission, write, or yolo argument, because a search never needs to write. Never passes `--disable-web-search`.

Input parameters:

- `background` (boolean): Run detached and return a runId immediately instead of waiting. Poll with the `status` tool. The run survives a restart of this MCP server. `false` is not a request.
- `cwd` (string): Absolute path. Working directory for the run. Passed as `--cwd`. Defaults to the current working directory.
- `effort` (string): Reasoning effort passed as `--effort`. Omit to use the server default. Values are passed through; the CLI rejects what the model does not advertise.
- `instructions` (string): Extra researcher guidance, appended verbatim to the prompt.
- `maxTurns` (integer): Maximum agentic turns. Passed as `--max-turns`. Headless only. No default — a cap is how a run gets cut off mid-research.
- `model` (string): Model id to pass as `--model`. Omit to use the server default. Unknown ids are rejected by the CLI, not by this server.
- `numResults` (integer): Prompt-level target for how many distinct sources to cite, not a backend limit. The CLI has no `--num-results` flag.
- `query` (string, required): The question to research. Passed as the body of a web-search-shaped prompt.
- `searchDepth` (string): Prompt-level search depth. `basic` (default) asks for one round; `full` asks for more than one, from different angles. The CLI has no `--search-depth` flag.

### `status` (~221 tokens)

Poll a background run

Poll a background `grok`, `review`, or `websearch` run, or list recent ones. A finished run replays the original tool result — same text, same metadata, same error flag — so background is a transport, not a second implementation. A run whose worker process has vanished is reported as `abandoned` rather than as still running. Pass `runId` to inspect one run, `waitMs` to block until it finishes, and omit `runId` to list recent runs.

Input parameters:

- `limit` (integer): Maximum rows to return in list mode. Default 20. Ignored when `runId` is set.
- `runId` (string): Id of a background run to inspect. Omit to list recent runs.
- `tail` (integer): Bytes of progress.log to include for a live run. Default 8192.
- `waitMs` (integer): Block up to this many milliseconds for the run to finish. Default 0. Ignored in list mode. A timed-out wait is not an error.

### `stop` (~95 tokens)

Stop a background run

Terminate a background `grok`, `review`, or `websearch` run: the worker and the grok process it spawned. Stopping an already-finished run is not an error. A run cancelled mid-flight may still have produced a resumable session id, which the result reports.

Input parameters:

- `runId` (string, required): The runId returned by a background `grok`, `review`, or `websearch` call.

### `help` (~27 tokens)

Grok CLI help

Show the grok CLI help text. Runs `grok --help` and returns its stdout.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/nuruvala-grok-build-mcp-server/grok-build-mcp-server#diagnostics

## Score history

- 2026-09-21: 91
- 2026-09-20: 90
- 2026-09-19: 93
- 2026-09-18: 93
- 2026-09-17: 93
- 2026-09-16: 93
- 2026-09-15: 92
- 2026-09-14: 92
- 2026-09-13: 91
- 2026-09-12: 91
- 2026-09-11: 90
- 2026-09-10: 90
- 2026-09-09: 90
- 2026-09-08: 89
- 2026-09-07: 89
- 2026-09-06: 88
- 2026-09-05: 88
- 2026-09-04: 87
- 2026-09-03: 87
- 2026-09-02: 86
- 2026-09-01: 86
- 2026-08-31: 85
- 2026-08-30: 85
- 2026-08-29: 84
- 2026-08-28: 84
- 2026-08-27: 83
- 2026-08-26: 83
- 2026-08-25: 81
- 2026-08-24: 81
- 2026-08-23: 80

## Common questions

### What is the Grok Build MCP server?

Grok Build is an MCP server listed in the public MCP registry as io.github.Nuruvala/grok-build-mcp-server. Run the Grok Build CLI as MCP tools: agent runs with live progress, code review, web research. This page covers its npm package (grok-build-mcp-server).

### Is the Grok Build MCP server safe to use?

Grok Build scores 91 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Grok Build MCP server expose?

Grok Build exposes 8 tools: check, grok, review, sessions, websearch, and 3 more. Their descriptions and schemas cost roughly 2,298 tokens of context every time the server is loaded.

### Is the Grok Build MCP server still maintained?

Grok Build is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Grok Build MCP server under?

Grok Build declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/grok-build-mcp-server
- Socket report: https://socket.dev/npm/package/grok-build-mcp-server
- Repository: https://github.com/Nuruvala/grok-build-to-claude
- Changelog RSS feed: https://verifymcp.io/servers/nuruvala-grok-build-mcp-server/grok-build-mcp-server.xml
- Changelog JSON feed: https://verifymcp.io/servers/nuruvala-grok-build-mcp-server/grok-build-mcp-server.json
- HTML version of this page: https://verifymcp.io/servers/nuruvala-grok-build-mcp-server/grok-build-mcp-server