mcp-graph-engine (utilitydelta/mcp-graph-engine) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 24 tools. No publisher has claimed this listing.

Warning

74/100

mcp-graph-engine

Item: mcp-graph-engine
Rating: 74
Author: M8ven

A graph database MCP server that lets AI assistants build, analyze, and visualize relationship graphs with algorithms like PageRank and cycle detection.

→ utilitydelta/mcp-graph-engine · listed on glama

Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

utilitydelta

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

🚨

Code appears obfuscated

1 file are unreadable to a human reviewer. Cannot audit what they do.

// tools this server exposes24 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

add_facts

Add facts (relationships) to the graph. Nodes are auto-created if they don't exist.

add_knowledge

Add knowledge using text DSL. Format: 'Subject relation Object' per line. Quote spaces: '\"Auth Service\" \"depends on\" \"User DB\"'. Type hints: 'Node:type rel Target:type'. Lines with # are comments.

list_graphs

List all graph sessions with statistics

delete_graph

Delete a graph session

get_graph_info

Get graph statistics and info

forget

Remove a node and its connected edges

forget_relationship

Remove an edge from the graph

shortest_path

Find shortest path between two nodes (Dijkstra). Fuzzy matches node labels.

all_paths

Find all simple paths between two nodes. Fuzzy matches labels.

pagerank

Calculate PageRank scores for node importance

connected_components

Find weakly connected components (node groups connected by paths)

find_cycles

Detect cycles (circular dependencies) in the graph

transitive_reduction

Remove redundant transitive edges (if A->B->C and A->C exist, remove A->C)

degree_centrality

Calculate in/out degree centrality to find highly connected nodes

subgraph

Extract subgraph with specified nodes and their interconnections. Fuzzy matches labels.

ask_graph

Pattern-matching queries: 'what depends on X', 'what does X depend on', 'path from X to Y', 'all paths from X to Y', 'cycles', 'most connected', 'orphans', 'components'. Use cypher_query for complex queries.

dump_context

Get complete graph summary: nodes by type, relationships, and insights (hubs, cycles, orphans).

import_graph

Import graph from DOT, CSV, GraphML, or JSON. Merges into existing graph.

export_graph

Export graph to DOT, CSV, GraphML, JSON, or Mermaid format.

create_from_mermaid

Create graph from Mermaid flowchart. Edge labels become relation types.

cypher_query

Execute Cypher query. Use DOUBLE QUOTES for strings. Edge types via WHERE r.relation = "type". Examples: MATCH (a)-[r]->(b) WHERE r.relation = "depends_on" RETURN a.label, b.label MATCH (n) WHERE n.type = "service" RETURN n.label MATCH (a)-[*1..3]->(b) RETURN DISTINCT b.label Node props: lab…

visualize_graph

Open browser visualization at localhost URL. Updates in real-time.

update_visualization_filter

Update Cypher filter for visualization. Empty string clears filter.

stop_visualization

Stop the visualization server.

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

configVIS_ENABLEDEnable/disable visualization

configVIS_PORTVisualization server port

configVIS_HOSTVisualization server host

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

24/24 tools missing one or more hints — add_facts (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); add_knowledge (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_graphs (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +21 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

18/24 tools referenced in tests (75%)

Write tests that reference each tool by name so every tool has at least one test.

No eval / new Function

1 eval() or new Function() call — dynamic code execution

Replace eval / Function with explicit parsing or safer alternatives.

Readable source code

1 file are minified or bundled, which is usually build output rather than concealment

Ship unminified, readable source.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Verified](https://m8ven.ai/badge/mcp/utilitydelta/mcp-graph-engine?variant=verified)](https://m8ven.ai/mcp/utilitydelta/mcp-graph-engine)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: 84ea6765a95955c283259bd9d4d01d858d0a4f62

code hash: ccfd4e4c155d60fdaa160fc2264c11980021daab0d03ecef19a76109825ae4fb

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client