Grok Build
NPM · GROK-BUILD-MCP-SERVER · SCANNED SEP 21
Run the Grok Build CLI as MCP tools: agent runs with live progress, code review, web research.
Available components
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. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 95 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to Nuruvala/grok-build-to-claude). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 31 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability66
- AI-judged instruction clarity (excellent).Pass
- 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. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
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.
npm · grok-build-mcp-server
claude mcp add nuruvala-grok-build-mcp-server -- npx -y grok-build-mcp-server
{
"mcpServers": {
"nuruvala-grok-build-mcp-server": {
"command": "npx",
"args": [
"-y",
"grok-build-mcp-server"
]
}
}
} {
"servers": {
"nuruvala-grok-build-mcp-server": {
"command": "npx",
"args": [
"-y",
"grok-build-mcp-server"
]
}
}
} codex mcp add nuruvala-grok-build-mcp-server -- npx -y grok-build-mcp-server
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"nuruvala-grok-build-mcp-server": {
"type": "local",
"command": [
"npx",
"-y",
"grok-build-mcp-server"
],
"enabled": true
}
}
} openclaw mcp add nuruvala-grok-build-mcp-server --command npx --arg -y --arg grok-build-mcp-server
mcp_servers:
nuruvala-grok-build-mcp-server:
command: "npx"
args: ["-y", "grok-build-mcp-server"] {
"McpServers": {
"nuruvala-grok-build-mcp-server": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"grok-build-mcp-server"
]
}
}
} assistant mcp add nuruvala-grok-build-mcp-server -t stdio -c npx -a -y grok-build-mcp-server
{
"mcpServers": {
"nuruvala-grok-build-mcp-server": {
"command": "npx",
"args": [
"-y",
"grok-build-mcp-server"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Sept 26 +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.
- 20 Sept 26 −3
- Stability: pass → 0.80 functional
- 19 Sept 26 0
- Stability: 0.97 → pass security
- 18 Sept 26 0
- Stability: pass → 0.97 functional
- 17 Sept 26 0
- Stability: 0.97 → pass security
- 16 Sept 26 +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.
- 14 Sept 26 +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.
- 12 Sept 26 +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.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Sept 2026 · Analysed npm/grok-build-mcp-server@0.2.5
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | Nuruvala/grok-build-to-claude |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/Nuruvala/grok-build-to-claude/.github/workflows/release.yml@refs/tags/v0.2.5 |
| Rekor log index | 2538830867 |
| Predicate type | https://slsa.dev/provenance/v1 |
| Subject digest | sha512:61f19ab4c27fa8a6a6f7d141379009c16c15caeea808c56b4ddf452df471127715113c8f68fa8736f3071b35ecfdee88bdefecbff39c6da30c7f34c4a |
Background: How many MCP packages publish verified provenance →
Dependencies 95 packages
| Packages resolved | 95 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
check Check Grok Build readiness ~54
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
grok Run Grok Build ~806
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 | yes | 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. |
No output schema declared.
No examples provided.
help Grok CLI help ~27
Show the grok CLI help text. Runs `grok --help` and returns its stdout.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
review Review a git diff ~455
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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. |
No output schema declared.
No examples provided.
sessions List Grok sessions ~238
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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. |
No output schema declared.
No examples provided.
status Poll a background run ~221
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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. |
No output schema declared.
No examples provided.
stop Stop a background run ~95
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.
| Name | Type | Req | Description |
|---|---|---|---|
| runId | string | yes | The runId returned by a background `grok`, `review`, or `websearch` call. |
No output schema declared.
No examples provided.
websearch Search the web with Grok Build ~402
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`.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 | yes | 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. |
No output schema declared.
No examples provided.
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.