# kiriya (npm · kiriya) Developer tools for files, git, ports, processes and more, the same on Windows, Linux and macOS - Trust score: 86/100 (high trust) - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-09-29 ## Components - npm · `kiriya`: 86/100 (this document), [markdown](https://verifymcp.io/servers/satpaingoo-kiriya/kiriya.md), [page](https://verifymcp.io/servers/satpaingoo-kiriya/kiriya) ## Channel facts - Registry: `npm` - Package: `kiriya` - Version: `0.1.2` - 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 2026-09-29. - **Supply Chain Security**: 100/100 - No malware found by supply-chain analysis. - No known CVEs affecting this package version or its production dependencies. - No install/post-install scripts declared. - No production dependencies, so there is no dependency health to assess. - **Provenance & Transparency**: 100/100 - Source repository is publicly reachable at the declared URL. - Cryptographically verified build provenance (signed, bound to SatPaingOo/kiriya). - Clear OSI-approved license (MIT). - Actively maintained (last published 4 days ago). - Publishes a security disclosure policy (SECURITY.md). - **Schema Quality & AI Usability**: 82/100 - AI-judged instruction clarity (excellent). - Tool/resource definitions use about 3127 tokens (~66/item across 47 items; 47 tools + 0 resources), lean. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 20/100 - Stability observed for 6 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. - Structured output schemas are declared (100% of tools); any adoption earns full credit. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - We read all 47 captured tool definition(s), and no name or description among them implies an irreversible operation. - An AI judge read all 48 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a current MCP spec version (2026-07-28). ## Install ### How do I install the kiriya MCP server? kiriya runs locally as an npm package, launched with npx -y kiriya. 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 satpaingoo-kiriya -- npx -y kiriya ``` ### Cursor ```json { "mcpServers": { "satpaingoo-kiriya": { "command": "npx", "args": [ "-y", "kiriya" ] } } } ``` ### VS Code ```json { "servers": { "satpaingoo-kiriya": { "command": "npx", "args": [ "-y", "kiriya" ] } } } ``` ### Codex ```bash codex mcp add satpaingoo-kiriya -- npx -y kiriya ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "satpaingoo-kiriya": { "type": "local", "command": [ "npx", "-y", "kiriya" ], "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add satpaingoo-kiriya --command npx --arg -y --arg kiriya ``` ### Hermes ```yaml mcp_servers: satpaingoo-kiriya: command: "npx" args: ["-y", "kiriya"] ``` ### Netclaw ```json { "McpServers": { "satpaingoo-kiriya": { "Transport": "stdio", "Command": "npx", "Arguments": [ "-y", "kiriya" ] } } } ``` ### Vellum ```bash assistant mcp add satpaingoo-kiriya -t stdio -c npx -a -y kiriya ``` ### Other ```json { "mcpServers": { "satpaingoo-kiriya": { "command": "npx", "args": [ "-y", "kiriya" ] } } } ``` ## 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. ### 2026-09-29 (score 86, +1) No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-28 (score 85, 0) - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ### 2026-09-27 (score 85, +1) No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-25 (score 84, +1) - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ### 2026-09-24 (score 83, +11) - [security regression] Tool safety: pass → unverified - [security improvement] Known CVEs: unverified → pass - [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. - [functional regression] Capabilities: pass → unverified - [functional regression] Tool coverage: 100 → unverified - [functional improvement] Stability: unverified → 0.03 - [functional improvement] Dependency health: unverified → pass - [functional] First check of Schema quality: unverified - [functional] Package version: 0.1.1 → 0.1.2 ### 2026-09-23 (score 72) First indexed and scored. ## MCP tools (47) ### `completion` (~40 tokens) Print the completion script for a shell; its first lines say how to load it Input parameters: - `shell` (string, required): bash, zsh, fish or powershell Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `completion.suggest` (~66 tokens) Print what can come next on a command line, for the completion scripts to show Input parameters: - `current` (string): The word being completed, which may be empty - `word` (array): A word before it on the command line, once for each word Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `config.get` (~28 tokens) Print one setting, one value per line Input parameters: - `key` (string, required): The setting's name Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `config.keys` (~15 tokens) List every setting kiriya reads Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `config.list` (~16 tokens) List the settings in the configuration file Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `config.path` (~22 tokens) Print where the configuration file is, whether or not it exists yet Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `convert.base64` (~89 tokens) Encode text or a file as base64, or decode base64 back to text Input parameters: - `decode` (boolean): Decode instead of encode - `file` (string): Read a file's exact bytes instead - `url` (boolean): Use the URL-safe alphabet, without padding - `value` (string): The text to convert; - or nothing reads what is piped in Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `convert.case` (~85 tokens) Change the case of text, line by line: kebab, snake, camel, pascal, constant, title, lower or upper Input parameters: - `file` (string): Read a file's exact bytes instead - `to` (string): The case to change to - `value` (string): The text to convert; - or nothing reads what is piped in Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `convert.hex` (~71 tokens) Encode text or a file as hexadecimal, or decode hexadecimal back to text Input parameters: - `decode` (boolean): Decode instead of encode - `file` (string): Read a file's exact bytes instead - `value` (string): The text to convert; - or nothing reads what is piped in Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `convert.json` (~86 tokens) Format, minify or check JSON, pointing at the line and column of an error Input parameters: - `check` (boolean): Only check it - `file` (string): Read a file's exact bytes instead - `minify` (boolean): Print it on one line - `value` (string): The text to convert; - or nothing reads what is piped in Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `convert.jwt` (~66 tokens) Decode a JWT's header and payload on this machine; the signature is never checked and nothing is sent Input parameters: - `file` (string): Read a file's exact bytes instead - `value` (string): The text to convert; - or nothing reads what is piped in Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `convert.time` (~91 tokens) Show a moment as ISO 8601, local time, and Unix seconds and milliseconds; now by default Input parameters: - `unit` (string): How to read a number: auto, seconds or ms; auto reads numbers below 100000000000 as seconds - `value` (string): Unix seconds or milliseconds, or a date such as 2026-01-31T12:00:00Z Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `convert.url` (~68 tokens) Percent-encode text for a URL, or decode it Input parameters: - `decode` (boolean): Decode instead of encode - `file` (string): Read a file's exact bytes instead - `value` (string): The text to convert; - or nothing reads what is piped in Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `docker.logs` (~94 tokens) Show the project's logs, optionally following them Input parameters: - `file` (string): The compose file; by default compose.yaml, compose.yml, docker-compose.yaml or docker-compose.yml here - `services` (array): The services to act on; every service by default - `tail` (string): How many lines to show from the end of each log, or all; 200 by default Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `docker.ps` (~67 tokens) List the containers of the compose project here, or every compose project Input parameters: - `file` (string): The compose file; by default compose.yaml, compose.yml, docker-compose.yaml or docker-compose.yml here - `projects` (boolean): List every compose project on this machine instead Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `doctor` (~29 tokens) Check what this machine gives kiriya: runtime, configuration, trash, clipboard, git, docker and plugins Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `env.check` (~66 tokens) Compare a .env file with its .env.example by variable name; values are never shown Input parameters: - `example` (string): The file listing the variables expected; .env.example by default - `file` (string): The file to check; .env by default Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `env.path` (~44 tokens) Check each folder in PATH, or another list variable, for missing, duplicate, empty and relative entries Input parameters: - `variable` (string): The variable to check; PATH by default Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `env.show` (~36 tokens) List environment variables, hiding values that look secret Input parameters: - `filter` (string): Only variables whose name contains this text, in any case Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `files.compare` (~66 tokens) Compare two files, or two folders, by content; exits 1 when they differ Input parameters: - `a` (string, required): The first file or folder - `all` (boolean): In folders, include hidden entries and dependency folders - `b` (string, required): The second file or folder Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `files.dupes` (~78 tokens) Find files with identical content, and the space their extra copies take Input parameters: - `all` (boolean): Include hidden entries and dependency folders such as node_modules - `folder` (string): The folder to search; the current folder by default - `min-size` (string): Ignore files smaller than this, such as 1MB Output parameters: - `applyFlag` (string) - `command` (string) - `data` - `error` (object) - `failures` (array) - `kind` (string) - `ok` (boolean) - `output` (string): What a program the command ran printed - `truncated` (array): Where the result was cut to fit, and how much - `warnings` (array) ### `files.find` (~213 tokens) Find files and folders by name, extension, type, size, age or emptiness Input parameters: - `all` (boolean): Include hidden entries and dependency folders such as node_modules - `empty` (boolean): Only empty files and folders - `ext` (array): Extensions, such as .ts,.tsx - `folder` (string): The folder to search; the current folder by default - `larger` (string): Larger than a size, such as 10KB - `limit` (string): Show at most this many results - `name` (string): A glob that ignores case, such as *.test.ts or src/**/index.* - `newer` (string): Modified within a time, such as 7d, or after a date