Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.aibenyclaude-coder/kira

NPM · KIRA-MCP · SCANNED SEP 21

Skills and Scars for AI agents - your agent records its failures and never repeats them.

Available components

0 this week 85 Trust /100
Trust breakdown (7 categories)

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 & Transparency74
  • Repository check failed: the declared repository URL redirects; it must resolve directly. See how to fix → View diagnostics → Fail
  • Cryptographically verified build provenance (signed, bound to aibenyclaude-coder/Kira). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 46 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability67
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2244 tokens (~224/item across 10 items; 10 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 Management80
  • Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage99
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 96% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 11 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
Install

How do I install the io.github.aibenyclaude-coder/kira MCP server?

io.github.aibenyclaude-coder/kira runs locally as an npm package, launched with npx -y kira-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · kira-mcp

# add to Claude Code
claude mcp add aibenyclaude-coder-kira -- npx -y kira-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "aibenyclaude-coder-kira": {
      "command": "npx",
      "args": [
        "-y",
        "kira-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "aibenyclaude-coder-kira": {
      "command": "npx",
      "args": [
        "-y",
        "kira-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add aibenyclaude-coder-kira -- npx -y kira-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "aibenyclaude-coder-kira": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "kira-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add aibenyclaude-coder-kira --command npx --arg -y --arg kira-mcp
# ~/.hermes/config.yaml
mcp_servers:
  aibenyclaude-coder-kira:
    command: "npx"
    args: ["-y", "kira-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "aibenyclaude-coder-kira": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "kira-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add aibenyclaude-coder-kira -t stdio -c npx -a -y kira-mcp
// mcp.json
{
  "mcpServers": {
    "aibenyclaude-coder-kira": {
      "command": "npx",
      "args": [
        "-y",
        "kira-mcp"
      ]
    }
  }
}
Changelog

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 −3
    • Stability: pass → 0.80 functional
  • 20 Sept 26 0
    • Stability: 0.97 → pass security
  • 19 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.

  • 17 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.

  • 15 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.

  • 14 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 13 Sept 26 0
    • Stability: 0.97 → pass security
  • 12 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.

Diagnostics

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/kira-mcp@0.11.0

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 aibenyclaude-coder/Kira
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/aibenyclaude-coder/Kira/.github/workflows/release.yml@refs/tags/v0.11.0
Rekor log index 2349237189
Predicate type https://slsa.dev/provenance/v1
Subject digest sha512:45de80520568079459e848bb4ffc216da0ffb1e805c2cb5570d80a8f0c3f98a2c18f545d69554c0163e812b3ed0ff5103a0f9bfa39f022db044ef9b7a

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 →

MCP tools · 10 exposed · ~1,783 tokens

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 →

Tool Tokens
kira_consent ~109

Set the telemetry consent level for kira_report. level='off' disables all uploads (local log still written). level='basic' uploads only anonymous core (skill_id, status, anonymous UUID, version, OS family, Node major). level='full' additionally uploads sanitized free-text note/context. Call with no arguments to query the current state. See PRIVACY.md for the exact wire format and redaction rules.

NameTypeReqDescription
levelstringNew consent level. Omit to query without changing.

No output schema declared.

No examples provided.

kira_get ~96

Get the full instructions for a specific skill or scar by ID. Call this AFTER kira_lookup to retrieve the step-by-step instructions for the skill you've chosen. lookup returns summaries (no instructions) to save tokens — use this tool to get the full details.

NameTypeReqDescription
idstringyesThe skill or scar ID (e.g., 'community.setup-stripe-nextjs.v1' or 'scar.vercel-env-vars-missing.v1').

No output schema declared.

No examples provided.

kira_lookup ~201

Look up skills (how to do it) AND scars (what to avoid) for a given keyword. Returns matching skills (community first, then vendor) and scars (critical first; your own recorded failures before shared ones, then by frequency). Personal scars recorded by kira_record_failure on this machine fire here too. The agent MUST: 1. Read ALL returned scars first — these are past failures. Avoid repeating them. 2. Read returned skills and choose the best fit for the project context. 3. ANNOUNCE the chosen skill's 'declaration' field to the user BEFORE executing. 4. Follow the skill's instructions step by step, watching for scar patterns.

NameTypeReqDescription
contextarrayOptional project context tags for disambiguation (e.g., ['nextjs', 'typescript']).
keywordstringyesThe firing keyword or phrase (e.g., 'deploy vercel', 'add auth'). Case-insensitive.

No output schema declared.

No examples provided.

kira_personal_brief ~203

Surface your most recent PERSONAL scars — the private, local-only failure notes recorded by kira_record_failure under ~/.kira/personal-scars/. Call this at the START of a session (ideally from a SessionStart hook) so you begin already aware of the walls you hit last time on this machine. Returns the top-N scars by recency (most recent first), each with its mistake and what to do instead. Pass 'limit' to change how many, and 'contexts' to keep only scars relevant to the current project. Personal scars are LOCAL-ONLY — this reads them from disk and never touches the network.

NameTypeReqDescription
contextsarrayOptional project context tags (e.g., ['nextjs', 'typescript']). When given, only scars sharing at least one context are returned; untagged scars are always kept (they apply everywhere).
limitnumberHow many recent scars to return (default 5, max 50).

No output schema declared.

No examples provided.

kira_premortem ~251

Run a PRE-MORTEM before starting a task. Given a goal (and optional project context), return a heat map of the past failure patterns (scars, shared and personal) most likely to bite — ranked worst-first: critical before warning, your own recorded failures before the shared corpus, then by how many times the wall has been recorded (hit_count). Each hotspot includes the mistake, the fix ('instead'), a relative heat score, and estimated minutes saved by avoiding it, plus an aggregate prevention value. When nothing matches strictly, 'near_scars' lists the closest recorded scars instead. Call this FIRST for any non-trivial task to surface known traps up front, then read each hotspot's 'instead' and use kira_lookup / kira_route to plan the actual work.

NameTypeReqDescription
contextarrayOptional project context tags (e.g., ['nextjs', 'typescript']) to focus the heat map.
goalstringyesThe task you are about to start, in natural language (e.g., 'deploy a Next.js app to Vercel with Stripe').
top_knumberMax number of hotspots to return. Default 5, max 20.

No output schema declared.

No examples provided.

kira_record_failure ~385

Capture a retry or exception you just hit as a PERSONAL scar — a private, local-only failure note stored under ~/.kira/personal-scars/. Call this immediately after a task needed extra attempts or threw an error, so future runs on this machine can avoid the same wall. Provide 'title' (what went wrong), 'mistake' (what was done / the exception), and ideally 'instead' (what to do next time). All free text is sanitized (keys, paths, emails redacted) before it touches disk; the response's 'redactions' field reports anything that was rewritten, so check it and re-record if a redaction hit something that was not a secret. A 'malformed' field means this call's parameters were glued together in transport and a field's text was lost — re-record with one long field at a time. A 'folded' field means this was merged into an EXISTING scar as a recurrence: the returned scar is that older one and your title/mistake were not stored, so check 'folded.into_title' and re-record if it describes a different failure. Personal scars are LOCAL-ONLY — they are never uploaded, on any tier.

NameTypeReqDescription
contextsarrayProject context tags (e.g., ['nextjs', 'typescript']).
insteadstringWhat to do instead next time (the fix / avoidance strategy).
keywordsarrayFiring keywords so this scar surfaces on future lookups.
mistakestringyesWhat the agent did wrong, or the exception / retry cause. The pattern to recognize and avoid next time.
severitystringDefaults to 'warning'.
summarystringOptional one-line summary. Defaults to the title.
titlestringyesShort summary of what went wrong (becomes the scar title).

No output schema declared.

No examples provided.

kira_report ~180

Report the outcome of applying a Kira skill. ALWAYS call this after completing (or failing) a task guided by a Kira skill. Statuses: 'success' = worked first try, 'retry' = needed extra attempts, 'failure' = gave up. For 'retry' and 'failure', include a note describing what went wrong — this feeds the scar system so other agents don't repeat the same mistake.

NameTypeReqDescription
contextstringOptional sanitized snippet of agent context (project type, framework, etc.). Sent only when consent level is 'full'.
notestringWhat went wrong (for retry/failure). This becomes a scar for future agents. Sent to the telemetry server only when consent level is 'full'.
skill_idstringyesThe id of the skill that was applied.
statusstringyes

No output schema declared.

No examples provided.

kira_route ~144

Plan a complete route for a goal. Instead of looking up individual skills, describe what you want to achieve (e.g., 'build a web app', 'add payments') and Kira returns an ordered sequence of steps, each with its Skill and Scars. Use this FIRST when the user describes a broad goal rather than a specific task. Then execute each step in order, calling kira_report after each one.

NameTypeReqDescription
contextarrayProject context tags (e.g., ['nextjs', 'typescript']).
goalstringyesThe user's goal in natural language (e.g., 'build a nextjs app', 'add payments', 'deploy my app').

No output schema declared.

No examples provided.

kira_share_scar ~153

Promote one of YOUR personal scars into a community submission so every Kira user stops hitting that wall. Takes a personal scar id (from kira_personal_brief / kira_lookup), re-sanitizes it, generalizes it to the community scar shape, and returns a prefilled GitHub issue URL plus a gh CLI fallback. NOTHING is uploaded by this tool — show the result to the user and let them submit. Accepted scars earn contributor status (see RECIPROCITY notes in the repo).

NameTypeReqDescription
repostringTarget GitHub repo (default aibenyclaude-coder/Kira).
scar_idstringyesThe personal scar to share (must start with 'scar.personal.').

No output schema declared.

No examples provided.

kira_status ~61

Report what's currently loaded and configured: kira version, tier (free/pro), telemetry consent level, counts of skills/scars/routes available, and where the local report log lives. Call this whenever you need to know the install state without exhausting the keyword search via lookup.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Common questions

What is the io.github.aibenyclaude-coder/kira MCP server?

io.github.aibenyclaude-coder/kira is an MCP server listed in the public MCP registry as io.github.aibenyclaude-coder/kira. Skills and Scars for AI agents - your agent records its failures and never repeats them. This page covers its npm package (kira-mcp).

Is the io.github.aibenyclaude-coder/kira MCP server safe to use?

io.github.aibenyclaude-coder/kira scores 85 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 io.github.aibenyclaude-coder/kira MCP server expose?

io.github.aibenyclaude-coder/kira exposes 10 tools: kira_lookup, kira_report, kira_route, kira_get, kira_consent, and 5 more. Their descriptions and schemas cost roughly 1,783 tokens of context every time the server is loaded.

Is the io.github.aibenyclaude-coder/kira MCP server still maintained?

io.github.aibenyclaude-coder/kira 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 io.github.aibenyclaude-coder/kira MCP server under?

io.github.aibenyclaude-coder/kira declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.