KnowledgeRail
NPM · KNOWLEDGE-RAIL · SCANNED SEP 21
Persistent, evidence-backed project knowledge and task context for coding agents.
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
- 24 of 63 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to Deviank88/KnowledgeRail). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 13 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability65
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (fair).Partial
- Context-footprint check failed: tool/resource definitions use about 1731 tokens (~173/item across 10 items; 8 tools + 2 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage75
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 11% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% 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
- We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the KnowledgeRail MCP server?
KnowledgeRail runs locally as an npm package, launched with npx -y knowledge-rail. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · knowledge-rail
claude mcp add deviank88-knowledge-rail -- npx -y knowledge-rail
{
"mcpServers": {
"deviank88-knowledge-rail": {
"command": "npx",
"args": [
"-y",
"knowledge-rail"
]
}
}
} {
"servers": {
"deviank88-knowledge-rail": {
"command": "npx",
"args": [
"-y",
"knowledge-rail"
]
}
}
} codex mcp add deviank88-knowledge-rail -- npx -y knowledge-rail
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"deviank88-knowledge-rail": {
"type": "local",
"command": [
"npx",
"-y",
"knowledge-rail"
],
"enabled": true
}
}
} openclaw mcp add deviank88-knowledge-rail --command npx --arg -y --arg knowledge-rail
mcp_servers:
deviank88-knowledge-rail:
command: "npx"
args: ["-y", "knowledge-rail"] {
"McpServers": {
"deviank88-knowledge-rail": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"knowledge-rail"
]
}
}
} assistant mcp add deviank88-knowledge-rail -t stdio -c npx -a -y knowledge-rail
{
"mcpServers": {
"deviank88-knowledge-rail": {
"command": "npx",
"args": [
"-y",
"knowledge-rail"
]
}
}
} 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 0
- Stability: 0.97 → pass security
- 20 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.
- 19 Sept 26 −1
- Stability: pass → 0.93 functional
- 15 Sept 26 0
- Stability: 0.97 → pass security
- 14 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.
- 12 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.
- 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.
- 8 Sept 26 +16
- Malware scan: unverified → pass ▲ security
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/knowledge-rail@2.8.0
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 | Deviank88/KnowledgeRail |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/Deviank88/KnowledgeRail/.github/workflows/publish.yml@refs/tags/v2.8.0 |
| Rekor log index | 2749937280 |
| Predicate type | https://slsa.dev/provenance/v1 |
| Subject digest | sha512:95637663e3b1bc86876e043d81555b7059e99c60f25756c785d92ee069b11a4734d0d2c3dc8d89f1012f7fe642f0dcf317e48ba5e2527255582c7d107 |
Background: How many MCP packages publish verified provenance →
Dependencies 63 packages
| Packages resolved | 63 |
|---|---|
| Stale | 24 |
| 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 →
knowledge_admin ~185
Initialize/inspect/rebuild, client setup, lint/repair, drift, and migration.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | init=bootstrap;status=state;checkpoint=rebuild;client_setup=hooks;lint=validate links/repair;drift=anchors;migrate=upgrade. |
| backup | boolean | – | – |
| clients | array | – | – |
| dry_run | boolean | – | lint: false applies repair. |
| force | boolean | – | lint: repair nested wiki. |
| include_broken_links | boolean | – | – |
| include_missing | boolean | – | – |
| include_orphans | boolean | – | – |
| integrity_mode | string | – | – |
| migration_action | string | – | – |
| paths | array | – | – |
| run_id | string | – | – |
| scope | string | – | – |
| setup_mode | string | – | – |
| target_version | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| guidance | string | – | – |
| nextAction | object|null | yes | – |
| resultText | string | – | – |
| state | string | yes | – |
No examples provided.
knowledge_code ~177
Code index, symbols, callers, fallback.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | rebuild=recreate;search=find;symbol=definition;references=callers;read=URI;record_fallback=raw lookup. |
| fallback_reason | string | – | no_match|ambiguous|unresolved_import|unsupported_extension;else other |
| fallback_result_count | integer | – | – |
| fallback_result_paths | array | – | – |
| kinds | array | – | – |
| max_chars | integer | – | – |
| max_results | integer | – | – |
| path | string | – | – |
| path_prefixes | array | – | – |
| query | string | – | – |
| recovered_evidence | array | – | – |
| request_id | string | – | – |
| resource_uri | string | – | – |
| symbol | string | – | – |
| symbol_id | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| guidance | string | – | – |
| nextAction | object|null | yes | – |
| resultText | string | – | – |
| state | string | yes | – |
No examples provided.
knowledge_context ~148
Evidence/gaps, pages, search, and graph.
| Name | Type | Req | Description |
|---|---|---|---|
| changed_paths | array | – | – |
| heuristic_token_budget | integer | – | – |
| intent | string | – | – |
| max_depth | integer | – | – |
| max_evidence | integer | – | – |
| max_nodes | integer | – | – |
| max_results | integer | – | – |
| mode | string | – | task=evidence/gaps;list=pages;search=passages;graph=relations/dependencies. |
| objective | string | – | – |
| page_types | array | – | – |
| query | string | – | – |
| response_detail | string | – | – |
| retrieval_profile | string | – | – |
| view | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| guidance | string | – | – |
| nextAction | object|null | yes | – |
| resultText | string | – | – |
| state | string | yes | – |
No examples provided.
knowledge_document ~118
Write or review evidence-backed documents.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | write=save Markdown;review=delivery check. |
| client_facing | boolean | – | – |
| content | string | – | – |
| diagram_mode | string | – | – |
| document_type | string | yes | – |
| filename | string | yes | – |
| include_wiki_update_plan | boolean | – | – |
| language | string | – | – |
| overwrite | boolean | – | – |
| project_name | string | – | – |
| required_sections | array | – | – |
| title | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| guidance | string | – | – |
| nextAction | object|null | yes | – |
| resultText | string | – | – |
| state | string | yes | – |
No examples provided.
knowledge_document_context ~194
Document plans and section evidence.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | plan=design outline;section=collect evidence. |
| audience | string | – | – |
| diagram_mode | string | – | – |
| document_type | string | yes | – |
| heuristic_token_budget | integer | – | – |
| language | string | – | – |
| max_chars_per_page | integer | – | – |
| max_output_chars | integer | – | – |
| max_pages | integer | – | – |
| max_sections | integer | – | – |
| max_total_chars | integer | – | – |
| objective | string | – | – |
| page_paths | array | – | – |
| page_types | array | – | – |
| preferred_evidence | array | – | – |
| project_name | string | – | – |
| query | string | – | – |
| required_evidence | array | – | – |
| required_sections | array | – | – |
| retrieval_profile | string | – | – |
| section_title | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| guidance | string | – | – |
| nextAction | object|null | yes | – |
| resultText | string | – | – |
| state | string | yes | – |
No examples provided.
knowledge_files ~75
Controlled source files and PDFs: list, read, normalize to Markdown.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | list=sources;read=open;normalize=Markdown. |
| category | string | – | – |
| max_chars | integer | – | – |
| overwrite | boolean | – | – |
| path | string | – | – |
| pattern | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| guidance | string | – | – |
| nextAction | object|null | yes | – |
| resultText | string | – | – |
| state | string | yes | – |
No examples provided.
knowledge_ingest ~240
Source ingestion, claims, coverage, recovery.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | start=begin;next=read segment;apply_claims=integrate;record_segment=classify;source_status=coverage;evidence_status=debt;report=drafts. |
| claim_ids | array | – | – |
| claims | array | – | target:page_path,page_title,page_type;code_resource_uri=knowledge_code URI. Stakeholders:entity_key,role,organization,email_domain,affiliation. |
| evidence_refs | array | – | – |
| include_resolved | boolean | – | – |
| max_chars | integer | – | – |
| normalized_filename | string | – | – |
| page_refs | array | – | – |
| reason | string | – | – |
| recovery_event_id | string | – | – |
| recovery_events | array | – | – |
| recovery_page_refs | array | – | – |
| recovery_reason | string | – | – |
| recovery_resolution | string | – | – |
| report_filename | string | – | – |
| segment_id | string | – | – |
| segment_max_chars | integer | – | – |
| segment_status | string | – | – |
| total_evidence_used | integer | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| guidance | string | – | – |
| nextAction | object|null | yes | – |
| resultText | string | – | – |
| state | string | yes | – |
No examples provided.
knowledge_page ~145
Page CRUD and durable log.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | read=open;write=create;edit=replace;move=rename;delete=remove;append_log=event. |
| content | string | – | – |
| dry_run | boolean | – | – |
| entry | string | – | – |
| level | string | – | – |
| max_chars | integer | – | – |
| new_path | string | – | – |
| new_string | string | – | – |
| old_path | string | – | – |
| old_string | string | – | – |
| path | string | – | Wiki .md path; wiki/ maps to root. |
| replace_all | boolean | – | – |
| resource_uri | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| guidance | string | – | – |
| nextAction | object|null | yes | – |
| resultText | string | – | – |
| state | string | yes | – |
No examples provided.
What is the KnowledgeRail MCP server?
KnowledgeRail is an MCP server listed in the public MCP registry as io.github.Deviank88/knowledge-rail. Persistent, evidence-backed project knowledge and task context for coding agents. This page covers its npm package (knowledge-rail).
Is the KnowledgeRail MCP server safe to use?
KnowledgeRail scores 91 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 KnowledgeRail MCP server expose?
KnowledgeRail exposes 8 tools: knowledge_context, knowledge_page, knowledge_files, knowledge_ingest, knowledge_code, and 3 more. Their descriptions and schemas cost roughly 1,282 tokens of context every time the server is loaded.
Is the KnowledgeRail MCP server still maintained?
KnowledgeRail 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 KnowledgeRail MCP server under?
KnowledgeRail declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.