Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.zcsabbagh/knowledge-graph-mcp

PYPI · KNOWLEDGE-GRAPH-MCP · SCANNED SEP 20

Knowledge graph MCP for student learning with spaced repetition and mastery tracking

−15 this week 63 Trust /100
Trust breakdown (7 categories)

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 Security50
  • Malware scan not yet available for this package.Unverified
  • 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 15 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency31
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1096 tokens (~156/item across 7 items; 7 tools + 0 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 Management83
  • Stability observed for 25 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 Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 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
Install

How do I install the io.github.zcsabbagh/knowledge-graph-mcp server?

io.github.zcsabbagh/knowledge-graph-mcp runs locally as a PyPI package, launched with uvx knowledge-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.

pypi · knowledge-graph-mcp

# add to Claude Code
claude mcp add zcsabbagh-knowledge-graph-mcp -- uvx knowledge-graph-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "zcsabbagh-knowledge-graph-mcp": {
      "command": "uvx",
      "args": [
        "knowledge-graph-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "zcsabbagh-knowledge-graph-mcp": {
      "command": "uvx",
      "args": [
        "knowledge-graph-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add zcsabbagh-knowledge-graph-mcp -- uvx knowledge-graph-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "zcsabbagh-knowledge-graph-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "knowledge-graph-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add zcsabbagh-knowledge-graph-mcp --command uvx --arg knowledge-graph-mcp
# ~/.hermes/config.yaml
mcp_servers:
  zcsabbagh-knowledge-graph-mcp:
    command: "uvx"
    args: ["knowledge-graph-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "zcsabbagh-knowledge-graph-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "knowledge-graph-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add zcsabbagh-knowledge-graph-mcp -t stdio -c uvx -a knowledge-graph-mcp
// mcp.json
{
  "mcpServers": {
    "zcsabbagh-knowledge-graph-mcp": {
      "command": "uvx",
      "args": [
        "knowledge-graph-mcp"
      ]
    }
  }
}
Changelog

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.

  • 19 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 18 Sept 26 −14
    • Malware scan: pass → unverified security
    • Stability: 0.97 → pass security
  • 16 Sept 26 +16
    • Malware scan: unverified → pass security
  • 14 Sept 26 −14
    • Malware scan: pass → unverified security
  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 −4
    • Stability: pass → 0.77 functional
  • 10 Sept 26 +1
    • Stability: 0.97 → pass security
  • 8 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.

Diagnostics

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 20 Sept 2026 · Analysed pypi/knowledge-graph-mcp@0.1.0

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 15 packages
Packages resolved 15
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 7 exposed · ~1,065 tokens

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 →

Tool Tokens
add_edge ~188

Create a relationship between two concepts in the knowledge graph.

NameTypeReqDescription
reasoningExplanation of why this relationship exists
relation_typestringyesType of relationship. One of: - "prerequisite": Source must be learned before target - "builds_on": Target extends/deepens source concept - "related_to": Concepts are connected (bidirectional semanti…
source_conceptstringyesSource node ID or concept name
strengthnumberConfidence in the relationship from 0.0 to 1.0. Default 1.0.
target_conceptstringyesTarget node ID or concept name

Structured output declared, but exposes no named fields.

No examples provided.

add_node ~144

Create a new concept node in the knowledge graph.

NameTypeReqDescription
conceptstringyesHuman-readable name for the concept (e.g., "Quadratic Formula")
descriptionDetailed description of what this concept represents
difficultynumberEstimated cognitive load from 0.0 (easy) to 1.0 (hard). Default 0.5.
domainCategory/domain (e.g., "mathematics", "physics", "programming")
node_idCustom ID for the node. Auto-generated from concept if not provided.
tagsList of categorization tags (e.g., ["algebra", "equations"])

Structured output declared, but exposes no named fields.

No examples provided.

get_learning_path ~82

Get the ordered learning path to reach a target concept. Returns a topologically sorted list of prerequisites, highlighting which concepts the student still needs to learn (gaps).

NameTypeReqDescription
include_masteredbooleanWhether to include already-mastered concepts in the path
target_conceptstringyesThe goal concept to learn (node ID or concept name)

Structured output declared, but exposes no named fields.

No examples provided.

get_statistics ~38

Get summary statistics for learning progress.

NameTypeReqDescription
domainFilter statistics by domain (e.g., "mathematics"). If None, returns all.

Structured output declared, but exposes no named fields.

No examples provided.

query_graph ~201

Query the knowledge graph for learning insights.

NameTypeReqDescription
domainFilter results by domain (e.g., "mathematics")
limitintegerMaximum number of results to return. Default 10.
node_idFocus node for some queries (required for "prerequisites")
query_typestringyesType of query to execute. One of: - "prerequisites": All prerequisites for a concept (requires node_id) - "ready_to_learn": Concepts where all prerequisites are mastered - "due_for_review": Nodes whe…

Structured output declared, but exposes no named fields.

No examples provided.

read_subgraph ~169

Get the neighborhood around a concept for context.

NameTypeReqDescription
center_nodestringyesNode ID or concept name to center on
depthintegerHow many edge hops to traverse (1=direct connections, 2=neighbors of neighbors)
directionstringWhich edges to follow: - "upstream": Follow edges where center is target (prerequisites) - "downstream": Follow edges where center is source (what it unlocks) - "both": Follow edges in both directions
include_masterybooleanWhether to include mastery data in response
output_formatstringOutput format: - "json": Just the structured data - "mermaid": Just the Mermaid diagram - "both": Both JSON and Mermaid (default)

Structured output declared, but exposes no named fields.

No examples provided.

update_node ~243

Update a node's properties and record a review session.

NameTypeReqDescription
difficultyUpdate estimated difficulty (0.0-1.0)
mastery_applicationAbility to use in new contexts (0.0-1.0)
mastery_explanationAbility to teach/explain to others (0.0-1.0)
mastery_levelOverall mastery (0.0-1.0). Overrides dimensional calculation.
mastery_recallAbility to retrieve from memory (0.0-1.0)
misconception_detectedSpecific misconception observed (e.g., "confuses ± with +")
node_idstringyesID or concept name of the node to update
notesLLM observations about the student's understanding
qualitySM-2 review quality rating (0-5). Triggers spaced repetition scheduling. - 5: Perfect response - 4: Correct after hesitation - 3: Correct with serious difficulty - 2: Incorrect, but correct answer se…

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the io.github.zcsabbagh/knowledge-graph-mcp server?

io.github.zcsabbagh/knowledge-graph-mcp is listed in the public MCP registry as io.github.zcsabbagh/knowledge-graph-mcp. Knowledge graph MCP for student learning with spaced repetition and mastery tracking. This page covers its PyPI package (knowledge-graph-mcp).

Is the io.github.zcsabbagh/knowledge-graph-mcp server safe to use?

io.github.zcsabbagh/knowledge-graph-mcp scores 63 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 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 io.github.zcsabbagh/knowledge-graph-mcp server expose?

io.github.zcsabbagh/knowledge-graph-mcp exposes 7 tools: add_node, add_edge, update_node, query_graph, read_subgraph, and 2 more. Their descriptions and schemas cost roughly 1,065 tokens of context every time the server is loaded.

Is the io.github.zcsabbagh/knowledge-graph-mcp server still maintained?

io.github.zcsabbagh/knowledge-graph-mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.