com.kage-core/kage
NPM · @KAGE-CORE/KAGE-GRAPH-MCP · SCANNED SEP 24
Verified memory for coding agents: claims cited against code, stale withheld, savings receipts.
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 99 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 (GPL-3.0-only).Pass
- Actively maintained (last published 33 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability79
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 4519 tokens (~68/item across 66 items; 66 tools + 0 resources), lean.Pass
- 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 Coverage72
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 17% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "kage_context_slot_delete" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 66 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 com.kage-core/kage MCP server?
com.kage-core/kage runs locally as an npm package, launched with npx -y @kage-core/kage-graph-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 · @kage-core/kage-graph-mcp
claude mcp add com-kage-core-kage -- npx -y @kage-core/kage-graph-mcp
{
"mcpServers": {
"com-kage-core-kage": {
"command": "npx",
"args": [
"-y",
"@kage-core/kage-graph-mcp"
]
}
}
} {
"servers": {
"com-kage-core-kage": {
"command": "npx",
"args": [
"-y",
"@kage-core/kage-graph-mcp"
]
}
}
} codex mcp add com-kage-core-kage -- npx -y @kage-core/kage-graph-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"com-kage-core-kage": {
"type": "local",
"command": [
"npx",
"-y",
"@kage-core/kage-graph-mcp"
],
"enabled": true
}
}
} openclaw mcp add com-kage-core-kage --command npx --arg -y --arg @kage-core/kage-graph-mcp
mcp_servers:
com-kage-core-kage:
command: "npx"
args: ["-y", "@kage-core/kage-graph-mcp"] {
"McpServers": {
"com-kage-core-kage": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@kage-core/kage-graph-mcp"
]
}
}
} assistant mcp add com-kage-core-kage -t stdio -c npx -a -y @kage-core/kage-graph-mcp
{
"mcpServers": {
"com-kage-core-kage": {
"command": "npx",
"args": [
"-y",
"@kage-core/kage-graph-mcp"
]
}
}
} 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.
- 23 Sept 26 −3
- Stability: pass → 0.77 functional
- 22 Sept 26 +1
- Stability: 0.97 → pass security
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 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 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.
- 16 Sept 26 −3
- Stability: pass → 0.80 functional
- 15 Sept 26 +1
- Stability: 0.97 → pass security
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 10 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 24 Sept 2026 · Analysed npm/@kage-core/kage-graph-mcp@2.3.0
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 99 packages
| Packages resolved | 99 |
|---|---|
| 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 →
kage_reviewers ~85
Suggest reviewers for target or changed files from local git authorship, recent edits, and code-graph co-change ownership. Does not contact GitHub or external services.
| Name | Type | Req | Description |
|---|---|---|---|
| changed_files | array | – | Optional PR/branch changed files. If targets is omitted, these are used. |
| project_dir | string | yes | – |
| targets | array | – | File paths to review |
No output schema declared.
No examples provided.
kage_risk ~94
Assess modification risk for files using Kage's code graph plus local git history: dependents, impact surface, churn, ownership, co-change partners, and test gaps. Use before editing hotspot or shared files.
| Name | Type | Req | Description |
|---|---|---|---|
| changed_files | array | – | Optional PR/branch changed files. If targets is omitted, these are assessed. |
| project_dir | string | yes | – |
| targets | array | – | File paths to assess |
No output schema declared.
No examples provided.
kage_search ~138
Search the kage community knowledge graph for gotchas, patterns, configs, and architectural decisions across auth, database, payments, deployment, frontend, testing, and more. Returns node summaries ranked by relevance.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | – | Optional: restrict search to a specific domain. One of: auth, database, payments, deployment, frontend, testing, api-design, email, storage, ai-agents, security, performance, observability, infrastru… |
| query | string | yes | What you are looking for, e.g. 'prisma serverless connection', 'stripe webhook signature', 'JWT refresh token' |
No output schema declared.
No examples provided.
kage_session_replay ~65
Return a privacy-preserving replay digest for observed agent sessions: timeline, touched paths, commands, durable candidates, and distill actions without raw transcript text.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
| project_dir | string | yes | – |
| session_id | string | – | – |
No output schema declared.
No examples provided.
kage_sessions ~40
Summarize local agent observation sessions, durable capture candidates, and next distillation actions without exposing raw transcript replay.
| Name | Type | Req | Description |
|---|---|---|---|
| project_dir | string | yes | – |
No output schema declared.
No examples provided.
kage_setup_agent ~76
Generate MCP/setup instructions for Codex, Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Cline, Goose, Roo Code, Kilo Code, Claude Desktop, Aider, or generic MCP.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | yes | – |
| project_dir | string | yes | – |
| write | boolean | – | – |
No output schema declared.
No examples provided.
kage_setup_doctor ~36
Audit Kage setup across supported agents, including Claude Code ambient hook readiness when applicable.
| Name | Type | Req | Description |
|---|---|---|---|
| project_dir | string | yes | – |
No output schema declared.
No examples provided.
kage_structural_index ~52
Build the complete cache-backed structural index for large repos. This covers all supported source/config/doc files and writes .agent_memory/structural artifacts separate from learned memory.
| Name | Type | Req | Description |
|---|---|---|---|
| project_dir | string | yes | – |
No output schema declared.
No examples provided.
kage_supersede ~63
Mark one repo-local memory packet as superseded by a replacement packet and write bidirectional lineage edges.
| Name | Type | Req | Description |
|---|---|---|---|
| packet_id | string | yes | – |
| project_dir | string | yes | – |
| reason | string | – | – |
| replacement_packet_id | string | yes | – |
No output schema declared.
No examples provided.
kage_validate ~36
Validate repo-local Kage memory packets, pending packets, generated indexes, and sensitive-content checks.
| Name | Type | Req | Description |
|---|---|---|---|
| project_dir | string | yes | – |
No output schema declared.
No examples provided.
kage_verify_agent ~57
Verify that Kage is truly active for the current agent: config, repo policy, indexes, recall, code graph, and this live MCP tool reachability.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | yes | – |
| project_dir | string | yes | – |
No output schema declared.
No examples provided.
kage_verify_citations ~75
Verify that a memory packet's cited file paths still exist and that the memory is not stale, before trusting it. Pass an id to check one packet, or omit to audit all approved repo memory. Returns grounding and staleness for each.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | – | – |
| project_dir | string | yes | – |
No output schema declared.
No examples provided.
kage_workflow ~204
Kage memory workflow (this tool performs no action; it returns this loop). 1) Start every task with kage_context (project_dir + the task as query): it validates memory, recalls relevant packets, and queries the code and knowledge graphs in one call. 2) Do the work, preferring repo memory over public context. 3) Capture reusable learnings with kage_learn — bug causes and verified fixes, conventions, decisions, gotchas, run/test/build commands. Wrap anything that must never leave the repo in <private>...</private> tags; private spans are stripped before sharing. 4) After meaningful file changes, call kage_refresh so indexes, graphs, and stale-memory checks stay current. 5) Before finishing a branch, call kage_pr_summarize then kage_pr_check. Recall receipts show estimated tokens saved versus rediscovery; report memory quality with kage_feedback (helpful/wrong/stale).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
kage_workspace ~77
Summarize a local multi-repo workspace: discovered git repos, Kage memory coverage, code graph counts, package dependencies, route contracts, topic/event contracts, and cross-repo co-change links between repos. Use when a task spans multiple sibling repos.
| Name | Type | Req | Description |
|---|---|---|---|
| project_dir | string | yes | Workspace root directory to scan for git repos |
No output schema declared.
No examples provided.
kage_workspace_recall ~86
Recall Kage memory across every indexed repo in a local workspace and rank the combined hits. Use for cross-repo teammate knowledge and shared context.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max combined hits to return (default 8) |
| project_dir | string | yes | Workspace root directory to scan for git repos |
| query | string | yes | Question or task to recall across repos |
No output schema declared.
No examples provided.
kage_xray ~47
Return a first-use Repo X-Ray: code structure layers for entry points, core files, risk, tests, memory overlay, and knowledge gaps.
| Name | Type | Req | Description |
|---|---|---|---|
| project_dir | string | yes | – |
No output schema declared.
No examples provided.
What is the com.kage-core/kage MCP server?
com.kage-core/kage is an MCP server listed in the public MCP registry as com.kage-core/kage. Verified memory for coding agents: claims cited against code, stale withheld, savings receipts. This page covers its npm package (@kage-core/kage-graph-mcp).
Is the com.kage-core/kage MCP server safe to use?
com.kage-core/kage scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 24 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 com.kage-core/kage MCP server expose?
com.kage-core/kage exposes 66 tools: kage_context, kage_search, kage_fetch, kage_list_domains, kage_recall, and 61 more. Their descriptions and schemas cost roughly 4,519 tokens of context every time the server is loaded.
Is the com.kage-core/kage MCP server still maintained?
com.kage-core/kage is still listed as active in the MCP registry. We last reached this channel on 24 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 com.kage-core/kage MCP server under?
com.kage-core/kage declares the GPL-3.0-only licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.