Academic Research Kernel
PYPI · ACADEMIC-RESEARCH-KERNEL · SCANNED SEP 21
Deterministic research state, evidence validation and statistical recomputation.
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 Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 1 of 20 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
- 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
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 0 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability73
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 1025 tokens (~85/item across 12 items; 12 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage98
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 95% 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; "decision_ledger_validate" implies "execute" 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 12 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
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
How do I install the Academic Research Kernel MCP server?
Academic Research Kernel runs locally as a PyPI package, launched with uvx academic-research-kernel. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · academic-research-kernel
claude mcp add xngg1021-academic-research-kernel -- uvx academic-research-kernel
{
"mcpServers": {
"xngg1021-academic-research-kernel": {
"command": "uvx",
"args": [
"academic-research-kernel"
]
}
}
} {
"servers": {
"xngg1021-academic-research-kernel": {
"command": "uvx",
"args": [
"academic-research-kernel"
]
}
}
} codex mcp add xngg1021-academic-research-kernel -- uvx academic-research-kernel
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"xngg1021-academic-research-kernel": {
"type": "local",
"command": [
"uvx",
"academic-research-kernel"
],
"enabled": true
}
}
} openclaw mcp add xngg1021-academic-research-kernel --command uvx --arg academic-research-kernel
mcp_servers:
xngg1021-academic-research-kernel:
command: "uvx"
args: ["academic-research-kernel"] {
"McpServers": {
"xngg1021-academic-research-kernel": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"academic-research-kernel"
]
}
}
} assistant mcp add xngg1021-academic-research-kernel -t stdio -c uvx -a academic-research-kernel
{
"mcpServers": {
"xngg1021-academic-research-kernel": {
"command": "uvx",
"args": [
"academic-research-kernel"
]
}
}
} 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 66
First indexed and scored.
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 pypi/academic-research-kernel@2.0.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 20 packages
| Packages resolved | 20 |
|---|---|
| Stale | 1 |
| 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 →
academic_check_percentage ~71
Check if a reported percentage and count can mathematically arise from a sample size.
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | yes | Observed count (numerator) |
| percent | number | yes | Reported percentage (e.g. 12.5) |
| sample_size | integer | – | Optional total sample size (denominator) |
No output schema declared.
No examples provided.
academic_recompute_statistics ~151
Recompute statistical claims (effect sizes, p-values, t-tests, CIs, OR/RR) to detect rounding errors or impossible figures.
| Name | Type | Req | Description |
|---|---|---|---|
| df | number | – | Degrees of freedom (integer or Welch fractional) |
| mean1 | number | – | Group 1 mean |
| mean2 | number | – | Group 2 mean |
| n1 | integer | – | Group 1 size |
| n2 | integer | – | Group 2 size |
| p_value | number | – | Reported p-value |
| sd1 | number | – | Group 1 SD |
| sd2 | number | – | Group 2 SD |
| t_stat | number | – | Reported t-statistic |
No output schema declared.
No examples provided.
academic_scfabric_hardware_probe ~34
Probe local hardware accelerators (CUDA, ROCm, MPS, XPU) and execution environments.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
claim_evidence_trace ~94
Trace all supporting and refuting evidence anchors and attached receipts for a given claim.
| Name | Type | Req | Description |
|---|---|---|---|
| claim_id | string | yes | Target claim identifier to trace. |
| content_payloads | object | – | Authorized base64 content by lineage entity ID; maximum total 10 MiB. |
| graph | object | yes | ClaimEvidenceGraph export dictionary. |
| receipts | object | – | Physical receipt registry keyed by receipt ID or payload SHA-256. |
No output schema declared.
No examples provided.
claim_evidence_validate ~84
Validate the structural integrity, cycles, and cryptographic receipt bindings of a ClaimEvidenceGraph snapshot.
| Name | Type | Req | Description |
|---|---|---|---|
| content_payloads | object | – | Authorized base64 content by lineage entity ID; maximum total 10 MiB. |
| graph | object | yes | ClaimEvidenceGraph export dictionary. |
| receipts | object | – | Physical receipt registry keyed by receipt ID or payload SHA-256. |
No output schema declared.
No examples provided.
decision_ledger_validate ~77
Execute complete four-gate verification over a Decision Ledger export dictionary.
| Name | Type | Req | Description |
|---|---|---|---|
| content_payloads | object | – | Authorized base64 content by lineage entity ID; maximum total 10 MiB. |
| ledger | object | yes | DecisionLedger export dictionary. |
| receipts | object | – | Physical receipt registry keyed by receipt ID or payload SHA-256. |
No output schema declared.
No examples provided.
decision_trace ~93
Trace causal ancestry, basis dependencies, outcome corrections, and lifecycle state history for a decision.
| Name | Type | Req | Description |
|---|---|---|---|
| content_payloads | object | – | Authorized base64 content by lineage entity ID; maximum total 10 MiB. |
| decision_id | string | yes | The decision identifier to trace. |
| ledger | object | yes | DecisionLedger export dictionary. |
| receipts | object | – | Physical receipt registry keyed by receipt ID or payload SHA-256. |
No output schema declared.
No examples provided.
research_artifact_ingest ~140
Deterministically ingest a scholarly artifact envelope into kernel state (ResearchObjects, CEG, and Ledger).
| Name | Type | Req | Description |
|---|---|---|---|
| bindings | object | – | Optional explicit bindings (e.g. {'decision_id': '...', 'claim_id': '...'}). |
| content_payloads | object | – | Authorized base64 content by lineage entity ID; maximum total 10 MiB. |
| dry_run | boolean | – | If true, simulates ingestion and returns plan without committing state. |
| envelope | object | yes | The ResearchArtifactEnvelope to ingest. |
| state | object | – | Optional initial kernel state snapshot (containing 'ceg', 'ledger', 'objects'). |
No output schema declared.
No examples provided.
research_artifact_validate ~104
Validate a ResearchArtifactEnvelope against its schema and verify its cryptographic payload SHA-256 without side effects.
| Name | Type | Req | Description |
|---|---|---|---|
| bindings | object | – | – |
| content_payloads | object | – | Authorized base64 content by lineage entity ID; maximum total 10 MiB. |
| envelope | object | yes | The ResearchArtifactEnvelope dictionary to validate. |
| receipts | object | – | Optional physical receipt registry required to replay receipt-backed CEG or Ledger snapshots. |
| state | object | – | – |
No output schema declared.
No examples provided.
research_lineage_trace ~56
Trace backward provenance ancestry for a specified entity within a LineageGraph snapshot.
| Name | Type | Req | Description |
|---|---|---|---|
| lineage_graph | object | yes | Exported LineageGraph dictionary. |
| target_entity_id | string | yes | The entity ID to trace upstream lineage from. |
No output schema declared.
No examples provided.
research_object_resolve ~42
Resolve and aggregate candidate bibliographic/identity records into discrete five-state equivalence judgments.
| Name | Type | Req | Description |
|---|---|---|---|
| records | array | yes | List of candidate metadata records sharing possible identifiers. |
No output schema declared.
No examples provided.
research_receipt_verify ~79
Verify an AcademicEvidenceReceipt or LineageReceipt against a strongly typed ReceiptRef.
| Name | Type | Req | Description |
|---|---|---|---|
| content_payloads | object | – | Authorized base64 content by lineage entity ID; maximum total 10 MiB. |
| receipt_payload | object | yes | The full physical receipt payload dictionary to verify. |
| receipt_ref | object | yes | The ReceiptRef reference dictionary. |
No output schema declared.
No examples provided.
What is the Academic Research Kernel MCP server?
Academic Research Kernel is an MCP server listed in the public MCP registry as io.github.xngg1021/academic-research-kernel. Deterministic research state, evidence validation and statistical recomputation. This page covers its PyPI package (academic-research-kernel).
Is the Academic Research Kernel MCP server safe to use?
Academic Research Kernel scores 66 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. 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 Academic Research Kernel MCP server expose?
Academic Research Kernel exposes 12 tools: research_artifact_validate, research_artifact_ingest, research_receipt_verify, research_object_resolve, research_lineage_trace, and 7 more. Their descriptions and schemas cost roughly 1,025 tokens of context every time the server is loaded.
Is the Academic Research Kernel MCP server still maintained?
Academic Research Kernel 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.