io.github.primeline-ai/kairn
MCPB · KAIRN-0.3.1.MCPB
Local-first knowledge engine for AI agents: memory, graph, and recall over MCP.
Available components
Last scanned (3 hours ago)
Scores higher than 90% of MCPB servers
Category Memory and Knowledge
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 Security12
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs were checked across the 19 of 19 dependencies we could resolve, so this covers what we could see, not the whole tree.Partial
- Install-script risk not yet assessed.Unverified
- 2 of 19 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 5 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability82
- 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
- Tool/resource definitions use about 1957 tokens (~78/item across 25 items; 22 tools + 3 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management63
- Stability observed for 19 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
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "kn_remove" implies "remove" 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 23 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
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.
- 17 Oct 26 +40
- Injection markers: unverified → pass ▲ security
- Stability: unverified → 0.63 ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Schema quality: unverified → 100 ▲ functional
- Package version: 0.2.1 → 0.3.1 functional
- 15 Oct 26 0
- Stability: Stability not yet verified: this server's registry entry declares environment variables (an API key or similar), and its server did not start in our sandbox, so we have no schema to compare. security
- Tool safety: Tool safety not yet verified: this server's registry entry declares environment variables (an API key or similar), and its server did not start in our sandbox, so we have no tool text to scan. security
- Security disclosure: unverified → fail ▼ functional
- Schema quality: Schema quality not yet verified: this server's registry entry declares environment variables (an API key or similar), and its server did not start in our sandbox, so we have no schema to assess. functional
- Capabilities: Protocol version not yet verified: this server's registry entry declares environment variables (an API key or similar), and its server did not start in our sandbox, so we never saw its MCP handshake. functional
- Tool coverage: Tool coverage not yet verified: this server's registry entry declares environment variables (an API key or similar), and its server did not start in our sandbox, so we have no tool definitions to assess. functional
- 14 Oct 26 0
- Security disclosure: fail → unverified ▼ functional
- 12 Oct 26 0
- Tool safety: Tool safety not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet. security
- Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
- Capabilities: Protocol version not yet verified: we do not have a sandbox capture of the MCP handshake this version of the package performs yet. functional
- Tool coverage: Tool coverage not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet. functional
- Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. functional
- Package version: 0.2.1 → 0.3.1 functional
- 10 Oct 26 −31
- Tool safety: pass → unverified ▼ security
- Stability: Stability not yet verified: this server's registry entry declares environment variables (an API key or similar), and its server did not start in our sandbox, so we have no schema to compare. security
- Tool coverage: 100 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- 28 Sept 26 +31
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Schema quality: unverified → 100 ▲ functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: 0 functional
- First check of Schema quality: pass functional
- First check of Schema quality: good functional
- First check of Tool coverage: 100 functional
- First check of Tool coverage: 100 functional
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 27 Sept 26 +4
- Known CVEs: unverified → partial ▲ security
- Security disclosure: unverified → fail ▼ functional
- Dependency health: unverified → 0.98 ▲ functional
- 26 Sept 26 −4
- Known CVEs: partial → unverified ▼ security
- Security disclosure: fail → unverified ▼ functional
- Dependency health: 0.98 → unverified ▼ functional
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 17 Oct 2026 · Analysed mcpb/https://github.com/primeline-ai/kairn/releases/download/v0.3.1/kairn-0.3.1.mcpb@0.3.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | mcpb |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Dependencies 19 packages
| Packages resolved | 19 |
|---|---|
| Stale | 2 |
| 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 →
kn_add ~69
Add node to knowledge graph. Auto-links via FTS5.
| Name | Type | Req | Description |
|---|---|---|---|
| description | – | – | Node description |
| name | string | yes | Node name |
| namespace | string | – | Namespace |
| tags | – | – | Tags for categorization |
| type | string | yes | Node type (concept, pattern, etc.) |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_connect ~80
Create typed, weighted edge between nodes.
| Name | Type | Req | Description |
|---|---|---|---|
| created_by | – | – | Who/what created this edge (for provenance) |
| edge_type | string | yes | Relationship type |
| source_id | string | yes | Source node ID |
| target_id | string | yes | Target node ID |
| weight | number | – | Edge weight 0.0-1.0 |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_context ~49
Keywords to relevant subgraph with progressive disclosure.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | summary or full |
| keywords | string | yes | Keywords to find relevant context for |
| limit | integer | – | Max results |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_crossref ~39
Find similar solutions from other workspaces.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max results |
| problem | string | yes | Problem description to find solutions for |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_doctor ~108
Read-only Kairn health diagnostics. Returns a structured envelope with per-check verdicts and a roll-up summary. Identical JSON shape to `kairn doctor --json` (envelope parity). Safe to call any time; checks never mutate workspace state.
| Name | Type | Req | Description |
|---|---|---|---|
| check | – | – | Run a single check by ID; omit to run all. Known: check_lock_mode, check_fts_index_health, check_promoted_experience_consistency, check_namespace_distribution, check_orphan_edges |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_idea ~87
Create or update idea with graph links.
| Name | Type | Req | Description |
|---|---|---|---|
| category | – | – | Category classification |
| idea_id | – | – | Idea ID (omit to create new) |
| link_to | – | – | Node ID to link this idea to |
| score | – | – | Numerical score |
| status | – | – | Status: draft|evaluating|approved|implementing|done|archived |
| title | string | yes | Idea title |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_ideas ~52
List and filter ideas by status/score.
| Name | Type | Req | Description |
|---|---|---|---|
| category | – | – | Filter by category |
| limit | integer | – | Max results |
| offset | integer | – | Pagination offset |
| status | – | – | Filter by status |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_judge ~174
Record a typed relationship judgment between two nodes. Strict-mode wrapper around kn_connect: only the 5 canonical relation verbs (conflicts_with, supersedes, compatible, scoped, related) are accepted. Use after kn_learn returns a non-empty candidates[] list to assert how the new node relates to an existing one. For legacy or system-generated edges, use kn_connect (lax mode).
| Name | Type | Req | Description |
|---|---|---|---|
| confidence | number | – | Confidence 0.0-1.0; persisted as edge.weight |
| reason | – | – | Optional rationale stored in edge.properties.reason |
| relation | string | yes | One of the 5 canonical verbs: conflicts_with, supersedes, compatible, scoped, related |
| source_id | string | yes | Source node ID |
| target_id | string | yes | Target node ID |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_learn ~170
Store knowledge from conversation. Creates node (high) or experience (medium/low).
| Name | Type | Req | Description |
|---|---|---|---|
| confidence | string | – | high=permanent, medium=likely, low=exploratory |
| content | string | yes | What was learned/decided/discovered |
| context | – | – | Situation when this was learned |
| namespace | string | – | Namespace for multi-tenant isolation (default 'knowledge') |
| tags | – | – | Tags for categorization |
| type | string | yes | decision|pattern|solution|workaround|gotcha|preference |
| with_candidates | boolean | – | Return up to 5 FTS5-matched related nodes in candidates[] so the caller can decide whether to invoke kn_judge for a relationship verb. Set False for bulk-save scripts that do not need the hook. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_log ~65
Log progress or failure entry.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | What was done or what failed |
| next_step | – | – | Recommended next step |
| project_id | string | yes | Project ID |
| result | – | – | Outcome or error message |
| type | string | – | progress or failure |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_memories ~136
Experience search. Filters on time-decay, reports match-aware relevance.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max results |
| min_relevance | number | – | Minimum RECENCY 0.0-1.0 (time-decay), not match quality. A high value returns only recent experiences, however poorly they match the query. It gates on age ALONE, while the reported `relevance` is ma… |
| offset | integer | – | Pagination offset |
| text | – | – | Full-text search query |
| type | – | – | Filter by experience type |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_preference ~184
Capture a stated user preference at utterance time. The dedicated write path for preferences: stores a `preference`-type experience with the longest half-life of any type (durable by default). Call it the moment a preference is expressed - the host model hearing the preference is the extraction step; Kairn's server stays deterministic and never runs an LLM.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | The user preference as ONE explicit, standalone sentence (e.g. 'User prefers Adobe Premiere Pro tutorials focused on advanced settings'). You, the calling model, are the extractor: state the preferen… |
| context | – | – | Situation in which the preference was stated |
| namespace | string | – | Namespace for multi-tenant isolation (default 'knowledge') |
| tags | – | – | Tags for categorization (subject of the preference) |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_project ~77
Create or update project (upsert).
| Name | Type | Req | Description |
|---|---|---|---|
| goals | – | – | Project goals |
| name | string | yes | Project name |
| phase | – | – | Phase: planning|active|paused|done |
| project_id | – | – | Project ID (omit to create new) |
| stakeholders | – | – | Stakeholders |
| success_metrics | – | – | Success metrics / KPIs |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_projects ~38
List projects and switch active.
| Name | Type | Req | Description |
|---|---|---|---|
| active_only | boolean | – | Only show active projects |
| set_active | – | – | Project ID to set as active |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_promote_pending ~142
Promote experiences flagged by the auto-promote SQL trigger. The exp_auto_promote trigger sets needs_promotion=1 when an experience's access_count crosses 5 (via the read-path touch_accessed wiring from Phase 8). This tool consumes those flags and turns each flagged experience into a permanent graph node via the existing _promote() path. Idempotent: repeatedly safe to call; no-op when nothing is flagged. Returns stats including the list of newly created node ids.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum experiences to promote in this call. Bounds a single sweep so it cannot block on a large promotion backlog. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_prune ~55
Remove expired experiences (archive first).
| Name | Type | Req | Description |
|---|---|---|---|
| threshold | number | – | DELETES experiences whose RECENCY (time-decay age) is below this. NOT match quality - raising it deletes older rows regardless of how good they are. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_query ~82
Search nodes by text, type, tags, or namespace.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | summary or full |
| limit | integer | – | Max results |
| namespace | – | – | Filter by namespace |
| node_type | – | – | Filter by type |
| offset | integer | – | Pagination offset |
| tags | – | – | Filter by tags |
| text | – | – | Full-text search query |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_recall ~115
Surface relevant past knowledge for context.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max results |
| min_relevance | number | – | Minimum score 0.0-1.0. THE SCALE DIFFERS BY ROW TYPE: it gates node rows on match strength (bm25, or embedding cosine when semantic recall is on) and experience rows on recency (time-decay). One numb… |
| topic | – | – | Topic to recall knowledge about |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_related ~47
Find nodes connected to a starting point.
| Name | Type | Req | Description |
|---|---|---|---|
| depth | integer | – | Traversal depth |
| edge_type | – | – | Filter by edge type |
| node_id | string | yes | Starting node ID |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_remove ~53
Soft-delete node or edge. Supports undo.
| Name | Type | Req | Description |
|---|---|---|---|
| edge_type | – | – | Edge type |
| node_id | – | – | Node ID to remove |
| source_id | – | – | Edge source ID |
| target_id | – | – | Edge target ID |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_save ~82
Save experience with configurable decay.
| Name | Type | Req | Description |
|---|---|---|---|
| confidence | string | – | high|medium|low — affects decay rate |
| content | string | yes | What was learned/discovered |
| context | – | – | Situation when this was learned |
| tags | – | – | Tags for categorization |
| type | string | yes | solution|pattern|decision|workaround|gotcha|preference |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
kn_status ~17
Graph stats, health, and system overview.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
How do I install the io.github.primeline-ai/kairn MCP server?
io.github.primeline-ai/kairn ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, 0cc65ad4919fcb110c645d56bebfb7d57da4dad8702a29e5b46a650f6c113aa2; the commands to do that are on this page. If it does not match, do not open it.
mcpb · kairn-0.3.1.mcpb
Download bundleCheck the download matches the SHA-256 the MCP registry declares before you open it. If it does not match, do not open the file.
SHA-256
0cc65ad4919fcb110c645d56bebfb7d57da4dad8702a29e5b46a650f6c113aa2
macOS / Linux
echo "0cc65ad4919fcb110c645d56bebfb7d57da4dad8702a29e5b46a650f6c113aa2 kairn-0.3.1.mcpb" | shasum -a 256 -c
Windows (PowerShell)
(Get-FileHash -Algorithm SHA256 .\kairn-0.3.1.mcpb).Hash -eq "0cc65ad4919fcb110c645d56bebfb7d57da4dad8702a29e5b46a650f6c113aa2"
Run it in the folder you saved the bundle to, then open the file with an MCPB-capable host such as Claude Desktop.
What is the io.github.primeline-ai/kairn MCP server?
io.github.primeline-ai/kairn is an MCP server listed in the public MCP registry as io.github.primeline-ai/kairn. Local-first knowledge engine for AI agents: memory, graph, and recall over MCP. This page covers its MCPB bundle (https://github.com/primeline-ai/kairn/releases/download/v0.3.1/kairn-0.3.1.mcpb).
Is the io.github.primeline-ai/kairn MCP server safe to use?
io.github.primeline-ai/kairn scores 53 out of 100 on VerifyMCP. 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.primeline-ai/kairn MCP server expose?
io.github.primeline-ai/kairn exposes 22 tools: kn_add, kn_connect, kn_judge, kn_query, kn_remove, and 17 more. Their descriptions and schemas cost roughly 1,921 tokens of context every time the server is loaded.
What licence is the io.github.primeline-ai/kairn MCP server under?
io.github.primeline-ai/kairn declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.