# Hex Research (npm · @levnikolaevich/hex-research-mcp)

Research graph MCP for hypotheses, goals, runs, source quality, audits, and generated maps.

- Trust score: 77/100 (medium)
- Change this week: +31
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- npm · `@levnikolaevich/hex-research-mcp`: 77/100 (this document), [markdown](https://verifymcp.io/servers/levnikolaevich-hex-research-mcp/levnikolaevich-hex-research-mcp.md), [page](https://verifymcp.io/servers/levnikolaevich-hex-research-mcp/levnikolaevich-hex-research-mcp)

## Channel facts

- Registry: `npm`
- Package: `@levnikolaevich/hex-research-mcp`
- Version: `0.2.1`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-04.

- **Supply Chain Security**: 83/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known medium-severity CVE affects hono 4.12.33, reached via @modelcontextprotocol/sdk > hono. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (142 of 146), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to levnikolaevich/claude-code-skills).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 87 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1141 tokens (~71/item across 16 items; 16 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add levnikolaevich-hex-research-mcp -- npx -y @levnikolaevich/hex-research-mcp
```

### Codex

```bash
codex mcp add levnikolaevich-hex-research-mcp -- npx -y @levnikolaevich/hex-research-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "levnikolaevich-hex-research-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@levnikolaevich/hex-research-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add levnikolaevich-hex-research-mcp --command npx --arg -y --arg @levnikolaevich/hex-research-mcp
```

### Hermes

```yaml
mcp_servers:
  levnikolaevich-hex-research-mcp:
    command: "npx"
    args: ["-y", "@levnikolaevich/hex-research-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "levnikolaevich-hex-research-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@levnikolaevich/hex-research-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-04 (score 77, −1)

- [security regression] CVE-2026-69207 affects this package: medium
- [security regression] Known CVEs: partial → fail

### 2026-08-02 (score 78, +52)

- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Provenance: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] The attested source repository moved: levnikolaevich/claude-code-skills
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] License: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: MIT

### 2026-07-31 (score 26, −20)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (16)

### `index_hypotheses` (~58 tokens)

Index Hypotheses

Rebuild the local SQLite research graph from docs/hypotheses, docs/goals, and benchmark run manifests.

Input parameters:

- `path` (string): Project root containing docs/hypotheses, docs/goals, and benchmark/runs

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

### `verify_index` (~45 tokens)

Verify Research Index Inputs

Validate research frontmatter and run manifests without rebuilding the SQLite index.

Input parameters:

- `path` (string): Project root containing docs/hypotheses, docs/goals, and benchmark/runs

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

### `find_hypotheses` (~141 tokens)

Find Hypotheses

Search indexed hypotheses by status, goal, task state, source type/year, priority tier, or claim text.

Input parameters:

- `cited_source_type` (string): Cited source type filter
- `cited_source_year_min`: Minimum cited source year
- `claim_substring` (string): Case-insensitive claim substring
- `goal` (string): Goal id filter, e.g. G1
- `limit`: Maximum hypotheses to return
- `path` (string): Indexed project root
- `priority_tier`: Priority tier filter
- `status` (string): Hypothesis status filter
- `task_state` (string): Linked task state filter

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

### `inspect_hypothesis` (~73 tokens)

Inspect Hypothesis

Return a bounded structured view of one hypothesis, including goals, tasks, evidence, runs, sources, and edges.

Input parameters:

- `claim_substring` (string): Fallback selector by claim substring
- `id` (string): Canonical H## or G## id
- `path` (string): Indexed project root

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

### `find_evidence` (~67 tokens)

Find Evidence

Find evidence entries and cited sources, optionally scoped to one hypothesis and source/evidence type.

Input parameters:

- `id` (string): Hypothesis id
- `limit`: Maximum rows to return
- `path` (string): Indexed project root
- `type` (string): Evidence or source type

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

### `find_runs` (~97 tokens)

Find Runs

Find targeted or explicit comprehensive benchmark runs by run id, hypothesis id, type, and comprehensive flag; goal metrics derive only from explicit comprehensive runs.

Input parameters:

- `comprehensive` (boolean): Filter comprehensive runs
- `hypothesis` (string): Hypothesis id for targeted runs
- `id` (string): Run id
- `limit`: Maximum rows to return
- `path` (string): Indexed project root
- `type` (string): Run type

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

### `trace_lineage` (~68 tokens)

Trace Lineage

Trace bounded hypothesis lineage and dependency edges around a hypothesis id.

Input parameters:

- `depth`: Maximum traversal depth
- `direction` (string): Traversal direction
- `id` (string, required): Starting hypothesis id
- `limit`: Maximum nodes to return
- `path` (string): Indexed project root

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

### `analyze_topology` (~47 tokens)

Analyze Topology

Summarize graph node/edge counts and high-degree hubs without dumping the full graph.

Input parameters:

- `limit`: Maximum hub rows to return
- `path` (string): Indexed project root

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

### `audit_orphans` (~52 tokens)

Audit Orphans

Audit orphaned, stale, missing-evidence, missing-source, dead-branch, task, and goal-run gaps.

Input parameters:

- `limit`: Maximum issues to return
- `path` (string): Indexed project root

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

### `inspect_goal` (~77 tokens)

Inspect Goal

Return a bounded structured view of one goal, including parent/child goals, linked hypotheses, and derived metrics_current provenance or missing-metrics reason.

Input parameters:

- `claim_substring` (string): Fallback selector by claim substring
- `id` (string): Canonical H## or G## id
- `path` (string): Indexed project root

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

### `trace_goal_tree` (~49 tokens)

Trace Goal Tree

Trace the bounded goal decomposition tree around one goal id.

Input parameters:

- `id` (string, required): Starting goal id
- `limit`: Maximum goals to return
- `path` (string): Indexed project root

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

### `audit_goal_alignment` (~51 tokens)

Audit Goal Alignment

Audit hypothesis-goal links, active goals without live hypotheses, goals missing explicit comprehensive-run metrics, and coverage candidates.

Input parameters:

- `limit`: Maximum issues to return
- `path` (string): Indexed project root

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

### `analyze_progress` (~59 tokens)

Analyze Progress

Use git diff to identify changed research graph files and field-level frontmatter deltas that should be verified or reindexed.

Input parameters:

- `compare_against` (string): Git ref to compare against, default "HEAD"
- `path` (string): Project root

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

### `analyze_proposed` (~61 tokens)

Analyze Proposed Hypothesis

Check one indexed hypothesis for readiness gaps before promotion or implementation.

Input parameters:

- `claim_substring` (string): Fallback selector by claim substring
- `id` (string): Canonical H## or G## id
- `path` (string): Indexed project root

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

### `export_canvas` (~90 tokens)

Export JSON Canvas

Export a bounded JSON Canvas map of goals, hypotheses, runs, and their relationships.

Input parameters:

- `dry_run` (boolean): Preview canvas JSON without writing the file
- `mode` (string): merge preserves existing node positions; overwrite creates a fresh layout
- `output_path` (string): Canvas path relative to project root, default "docs/research-map.canvas"
- `path` (string): Indexed project root

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

### `export_research_map` (~106 tokens)

Export Research Map Markdown

Generate docs/research-map.md from canonical split researchgraph files. Dry-run by default; refuses unmarked legacy overwrite unless force is true.

Input parameters:

- `dry_run` (boolean): Preview generated markdown without writing; default true
- `force` (boolean): Allow replacing an unmarked legacy research-map.md after dry-run review
- `output_path` (string): Markdown path relative to project root, default "docs/research-map.md"
- `path` (string): Indexed project root

Output parameters:

- `details` (object)
- `follow_ups` (array)
- `message` (string)
- `next_action` (string)
- `provenance`
- `quality` (object)
- `reason` (string)
- `result`
- `status` (string)
- `summary` (object)
- `warnings` (array)

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/levnikolaevich-hex-research-mcp/levnikolaevich-hex-research-mcp#diagnostics

## Score history

- 2026-08-04: 77
- 2026-08-03: 78
- 2026-08-02: 78
- 2026-08-01: 26
- 2026-07-31: 26
- 2026-07-29: 46
- 2026-07-28: 46
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/@levnikolaevich/hex-research-mcp
- Socket report: https://socket.dev/npm/package/@levnikolaevich/hex-research-mcp
- Repository: https://github.com/levnikolaevich/claude-code-skills
- Changelog RSS feed: https://verifymcp.io/servers/levnikolaevich-hex-research-mcp/levnikolaevich-hex-research-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/levnikolaevich-hex-research-mcp/levnikolaevich-hex-research-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/levnikolaevich-hex-research-mcp/levnikolaevich-hex-research-mcp