Kimi MCP Server
NPM · @TRISHCHUK/KIMI-MCP-SERVER · SCANNED SEP 20
MCP server bridging AI assistants to Moonshot AI Kimi Code CLI for code analysis and review
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 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 115 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability75
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 2602 tokens (~185/item across 14 items; 14 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 Management93
- Stability observed for 28 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage92
- 93% of tools have a non-trivial description (not blank, and not just the tool's name).Partial
- 85% of tool parameters carry a description.Partial
- Structured output schemas are declared (29% of tools); any adoption earns full credit.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 14 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 Kimi MCP Server server?
Kimi MCP Server runs locally as an npm package, launched with npx -y @trishchuk/kimi-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 · @trishchuk/kimi-mcp-server
claude mcp add x51xxx-kimi-mcp-server -- npx -y @trishchuk/kimi-mcp-server
{
"mcpServers": {
"x51xxx-kimi-mcp-server": {
"command": "npx",
"args": [
"-y",
"@trishchuk/kimi-mcp-server"
]
}
}
} {
"servers": {
"x51xxx-kimi-mcp-server": {
"command": "npx",
"args": [
"-y",
"@trishchuk/kimi-mcp-server"
]
}
}
} codex mcp add x51xxx-kimi-mcp-server -- npx -y @trishchuk/kimi-mcp-server
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"x51xxx-kimi-mcp-server": {
"type": "local",
"command": [
"npx",
"-y",
"@trishchuk/kimi-mcp-server"
],
"enabled": true
}
}
} openclaw mcp add x51xxx-kimi-mcp-server --command npx --arg -y --arg @trishchuk/kimi-mcp-server
mcp_servers:
x51xxx-kimi-mcp-server:
command: "npx"
args: ["-y", "@trishchuk/kimi-mcp-server"] {
"McpServers": {
"x51xxx-kimi-mcp-server": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@trishchuk/kimi-mcp-server"
]
}
}
} assistant mcp add x51xxx-kimi-mcp-server -t stdio -c npx -a -y @trishchuk/kimi-mcp-server
{
"mcpServers": {
"x51xxx-kimi-mcp-server": {
"command": "npx",
"args": [
"-y",
"@trishchuk/kimi-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.
- 20 Sept 26 0
- Security disclosure: fail → unverified ▼ functional
- 19 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.
- 17 Sept 26 −2
- Stability: pass → 0.83 functional
- 16 Sept 26 0
- Stability: 0.97 → pass security
- 15 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 0
- Security disclosure: unverified → fail ▼ functional
- 13 Sept 26 +1
- Security disclosure: fail → unverified ▼ functional
- 11 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 20 Sept 2026 · Analysed npm/@trishchuk/kimi-mcp-server@0.2.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| 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 →
ask-kimi ~657
Execute Kimi Code CLI with file analysis (@syntax), session resume, MCP passthrough, and safety controls.
| Name | Type | Req | Description |
|---|---|---|---|
| addDirs | array | – | Additional writable directories (--add-dir, repeatable). |
| afk | boolean | – | --afk: auto-approve in away-from-keyboard mode (print mode implies this). |
| agent | string | – | Builtin agent spec to use (--agent). "default" or "okabe". |
| agentFile | string | – | Custom agent spec file (--agent-file). |
| cd | string | – | Working directory |
| config | – | – | Configuration overrides — string (JSON/TOML) or object passed via --config. |
| configFile | string | – | Path to a config file (TOML or JSON). |
| continueLatest | boolean | – | Use --continue to resume the most recent Kimi session in cwd. |
| dryRun | boolean | – | Return the resolved CLI argv as JSON without spawning Kimi. |
| finalOnly | boolean | – | Add --final-message-only — skip intermediate tool-call output. Default: true. |
| includeMetadata | boolean | – | Include tool-call metadata in response (only meaningful with stream-json). |
| maxRalphIterations | integer | – | Extra autonomous iterations after the first turn (--max-ralph-iterations, -1 = unlimited). |
| maxStepsPerTurn | integer | – | Cap steps in one turn (--max-steps-per-turn). |
| mcpConfigFile | string | – | Path to an MCP config file with `mcpServers` (passed via --mcp-config-file). |
| model | string | – | Optional model override. Known: kimi-for-coding, kimi-k2-6, kimi-k2-6-turbo, kimi-k2-thinking-turbo, kimi-k2-5, kimi-latest. If omitted, uses your Kimi CLI default (~/.kimi/config.toml). |
| outputFormat | string | – | Kimi --output-format. "text" (default for clean responses) or "stream-json" (JSONL with assistant + tool messages). |
| plan | boolean | – | Start in plan mode (--plan). For richer planning, prefer the plan-kimi tool. |
| prompt | string | yes | Task or question. Use @ to include files (e.g., '@largefile.ts explain'). |
| quiet | boolean | – | Use --quiet (= --print --output-format text --final-message-only). |
| resetSession | boolean | – | Clear session context before execution. Starts fresh conversation. |
| responseMode | string | – | Response verbosity: "clean" returns only the final answer (default), "full" includes tool calls and stderr execution log. |
| sessionId | string | – | Internal session ID for conversation continuity (workspace-isolated). |
| skillsDirs | array | – | Custom skills directories (--skills-dir, repeatable). Overrides default discovery. |
| thinking | boolean | – | Toggle thinking mode (overrides default_thinking from config). |
| timeout | number | – | Maximum execution time in milliseconds (optional) |
| workingDir | string | – | Working directory for execution (alias of cd) |
| yolo | boolean | – | ⚠️ --yolo: auto-approve everything (dangerous, full file access). |
No output schema declared.
No examples provided.
batch-kimi ~196
Delegate multiple atomic tasks to Kimi for batch processing. Ideal for repetitive operations, mass refactoring, and automated transformations.
| Name | Type | Req | Description |
|---|---|---|---|
| concurrency | integer | – | Maximum parallel Kimi processes when parallel=true. Default: min(task count, 4) |
| model | string | – | Optional model override applied to every task. Known: kimi-for-coding, kimi-k2-6, kimi-k2-6-turbo, kimi-k2-thinking-turbo, kimi-k2-5, kimi-latest. |
| parallel | boolean | – | Execute independent tasks in parallel |
| stopOnError | boolean | – | Stop execution if any task fails |
| tasks | array | yes | Array of atomic tasks to delegate to Kimi |
| timeout | number | – | Maximum execution time per task in milliseconds |
| workingDir | string | – | Working directory for execution |
| yolo | boolean | – | Auto-approve everything (typical for batch jobs) |
| Name | Type | Req | Description |
|---|---|---|---|
| failed | number | yes | – |
| results | array | yes | – |
| skipped | number | yes | – |
| successful | number | yes | – |
| total | number | yes | – |
No examples provided.
bg-kimi ~318
Run Kimi CLI as a detached background task. Subactions: start (returns taskId), status, tail (log output), stop, remove, list. Use for long-running autonomous work — the MCP call returns immediately and you poll status later.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Background task action. |
| addDirs | array | – | – |
| agent | string | – | – |
| agentFile | string | – | – |
| cd | string | – | – |
| label | string | – | Human-readable label to identify this task later. |
| lines | integer | – | Lines to return from log tail. |
| maxRalphIterations | integer | – | Extra autonomous iterations after the first turn. -1 = unlimited. |
| maxStepsPerTurn | integer | – | – |
| mcpConfigFile | – | – | – |
| model | string | – | Optional model override. Known: kimi-for-coding, kimi-k2-6, kimi-k2-6-turbo, kimi-k2-thinking-turbo, kimi-k2-5, kimi-latest. |
| plan | boolean | – | Start in plan mode. |
| prompt | string | – | Prompt (required for action=start). |
| signal | string | – | Signal for stop action. |
| skillsDirs | array | – | – |
| taskId | string | – | Task ID returned by action=start. |
| thinking | boolean | – | – |
| workingDir | string | – | – |
| yolo | boolean | – | --yolo: auto-approve everything (default for bg tasks: afk; pass yolo for full power). |
No output schema declared.
No examples provided.
brainstorm ~261
Generate creative ideas using structured frameworks with domain context and feasibility analysis.
| Name | Type | Req | Description |
|---|---|---|---|
| afk | boolean | – | Auto-approve in AFK mode |
| cd | string | – | Working directory |
| constraints | string | – | Limitations: budget, time, technical, legal, etc. |
| domain | string | – | Domain: software, business, creative, research, product, marketing, etc. |
| existingContext | string | – | Background info or previous attempts |
| ideaCount | integer | – | Number of ideas (default: 12, range: 5-30) |
| includeAnalysis | boolean | – | Include feasibility/impact analysis |
| methodology | string | – | Framework: divergent, convergent, scamper, design-thinking, lateral, auto (default) |
| model | string | – | Optional model override. Known: kimi-for-coding, kimi-k2-6, kimi-k2-6-turbo, kimi-k2-thinking-turbo, kimi-k2-5, kimi-latest. If omitted, uses your Kimi CLI default. |
| prompt | string | yes | Brainstorming challenge or question |
| thinking | boolean | – | Enable thinking mode for deeper reasoning during ideation. |
| yolo | boolean | – | ⚠️ Bypass all approvals |
No output schema declared.
No examples provided.
delegate-kimi ~294
Delegate an implementation task to Kimi in an isolated git worktree. Kimi runs autonomously (--yolo) on a fresh branch, optionally looping against a test command. Returns a taskId; later 'collect' to grab the diff. Safe: changes are sandboxed, caller reviews & applies.
| Name | Type | Req | Description |
|---|---|---|---|
| acceptanceCriteria | array | – | Bullet list of criteria the implementation must satisfy. |
| action | string | – | start: spawn delegated task; status: check progress; collect: stop + return diff + cleanup option. |
| autoTest | string | – | Shell command Kimi should run after editing to validate (e.g., "npm test"). If passed, Kimi is told to loop until it passes. |
| baseBranch | string | – | Branch/commit to base the worktree on (default: current HEAD of repo). |
| branchName | string | – | Name for the new branch in the worktree. Default: kimi/<random>. |
| cleanup | boolean | – | On collect: also run `git worktree remove` after grabbing the diff. |
| maxRalphIterations | integer | – | Extra autonomous iterations (Ralph mode). Default 5 (use -1 for unlimited). |
| model | string | – | – |
| task | string | – | What Kimi should accomplish (required for action=start). |
| taskId | string | – | – |
| workingDir | string | – | Repo root (default: resolved automatically). |
No output schema declared.
No examples provided.
digest-kimi ~310
Ingest many files at once and answer a focused question. Uses Kimi's 262K context to swallow whole modules / docs that don't fit in the caller's context. Walks directories, filters by extension, truncates oversized files, caps total payload. Returns a concentrated brief.
| Name | Type | Req | Description |
|---|---|---|---|
| exclude | array | – | Substrings to exclude from paths (matched against relative path). Default: node_modules, .git, dist, build. |
| extensions | array | – | Filter by extensions when walking dirs (e.g., [".ts", ".tsx"]). Default: all text-like files. |
| maxBytesPerFile | integer | – | Truncate any single file above this size. Default: 200 KB. |
| maxTotalBytes | integer | – | Stop adding files once the total payload exceeds this (Kimi context is ~262K tokens / ~1MB safe). Default: 8 MB. |
| model | string | – | – |
| paths | array | yes | Files or directories to ingest. Directories are walked. Globs are NOT expanded — pass concrete paths. |
| question | string | yes | Focused question to answer using the provided files (e.g., "explain auth flow", "find dead code"). |
| recursive | boolean | – | Walk into subdirectories. Default: true. |
| shape | string | – | summary: 1-paragraph; detailed: structured deep-dive; qa: focused answer to the question. |
| timeout | number | – | – |
| workingDir | string | – | – |
No output schema declared.
No examples provided.
health ~46
Check Kimi CLI installation, authentication, and session health
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | – | Optional session ID to check specific session health |
| verbose | boolean | – | Include detailed diagnostic information |
| Name | Type | Req | Description |
|---|---|---|---|
| issues | array | yes | – |
| kimiCli | object | yes | – |
| sessions | object | yes | – |
| status | string | yes | – |
No examples provided.
Help ~14
Show Kimi CLI help output
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list-sessions ~59
List active conversation sessions with metadata, or manage them (delete/clear)
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Action: list (default), delete (single session), clear (all sessions) |
| sessionId | string | – | Session ID for delete action |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| sessions | array | – | – |
| stats | object | – | – |
No examples provided.
metrics ~20
Expose Prometheus-formatted metrics for Kimi MCP server
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
ping ~19
Echo
| Name | Type | Req | Description |
|---|---|---|---|
| prompt | string | – | Message to echo |
No output schema declared.
No examples provided.
plan-kimi ~178
Generate a structured implementation plan using Kimi's --plan mode. Use BEFORE coding to get steps, files-to-touch, risks, and open questions. Distinct from ask-kimi: uses --plan flag (different system prompt) and parses structured output.
| Name | Type | Req | Description |
|---|---|---|---|
| acceptance | array | – | Acceptance criteria the plan must satisfy. |
| constraints | string | – | Hard constraints (must-not-touch areas, style rules, deadlines). |
| contextFiles | array | – | Paths/globs to include as @-references in the prompt. |
| format | string | – | Output shape. json (default) returns structured steps/risks; markdown returns a checklist. |
| goal | string | yes | What you want planned (a feature, refactor, investigation). |
| model | string | – | – |
| timeout | number | – | – |
| workingDir | string | – | – |
No output schema declared.
No examples provided.
review-changes ~217
Run a code review against the current repository using Kimi (collects git diff + structured review prompt).
| Name | Type | Req | Description |
|---|---|---|---|
| base | string | – | Review changes against a specific base branch (e.g., "main", "develop") |
| commit | string | – | Review changes introduced by a specific commit SHA |
| model | string | – | Optional model override. Known: kimi-for-coding, kimi-k2-6, kimi-k2-6-turbo, kimi-k2-thinking-turbo, kimi-k2-5, kimi-latest. If omitted, uses your Kimi CLI default. |
| prompt | string | – | Custom review instructions or focus areas (optional) |
| thinking | boolean | – | Enable thinking mode for deeper review (recommended). |
| timeout | number | – | Maximum execution time in milliseconds |
| title | string | – | Optional title for the review summary |
| uncommitted | boolean | – | Review staged + unstaged + untracked changes (working tree) |
| workingDir | string | – | Working directory to run the review in |
No output schema declared.
No examples provided.
version ~13
Display version and system information
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| kimiCli | string | – | – |
| mcpServer | string | yes | – |
| nodeJs | string | yes | – |
| platform | string | yes | – |
No examples provided.
What is the Kimi MCP Server server?
Kimi MCP Server is listed in the public MCP registry as io.github.x51xxx/kimi-mcp-server. MCP server bridging AI assistants to Moonshot AI Kimi Code CLI for code analysis and review. This page covers its npm package (@trishchuk/kimi-mcp-server).
Is the Kimi MCP Server server safe to use?
Kimi MCP Server scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. 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 Kimi MCP Server server expose?
Kimi MCP Server exposes 14 tools: ask-kimi, batch-kimi, review-changes, brainstorm, bg-kimi, and 9 more. Their descriptions and schemas cost roughly 2,602 tokens of context every time the server is loaded.
Is the Kimi MCP Server server still maintained?
Kimi MCP Server is still listed as active in the MCP registry. We last reached this channel on 20 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 Kimi MCP Server server under?
Kimi MCP Server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.