Can I use Dijkstra for graphs with negative weights?

No. Dijkstra is designed for graphs with non-negative weights. For graphs with negative weights, you should use the Bellman-Ford capability.

What makes A* different from Dijkstra?

A* uses spatial heuristics like Manhattan or Euclidean distance to find the path more efficiently than Dijkstra.

How do I use this with Claude or Cursor?

You connect to the Vinkius-hosted MCP once. After that, your agent in Claude, Cursor, or Windsurf will automatically see these capabilities as available functions.

Does this MCP handle directed graphs?

Yes. The engine can calculate paths for both directed and undirected weighted graphs.

Can it detect infinite loops?

Yes. The Bellman-Ford capability is specifically designed to detect negative cycles that would cause infinite cost-reduction loops.

When should I use the Dijkstra capability?

Use dijkstra when you are certain that all edge weights in your graph are zero or positive. It is highly efficient for standard shortest-path queries.

Can I use A* search without a heuristic?

The astar capability requires a valid heuristicType (either EUCLIDEAN or MANSDT) to guide its search. Without a spatial estimate, the algorithm cannot function as intended.

How does the engine handle negative edge weights?

For graphs with negative weights, you must use bellman_ford. This capability is specifically designed to process negative edges and identify if a negative cycle exists in your graph.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Shortest Path Engine to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Calculate precise routes through complex weighted networks.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 3 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through Shortest Path Engine.

01
Astar
A* search finds the shortest path using spatial heuristics like Manhattan or Euclidean distance. It is best for guided searches rather than simple unweighted graphs.
02
Bellman ford
Bellman-Ford scans the graph to find shortest paths even when negative edge weights are present. It also detects negative cycles that would cause infinite cost loops.
03
Dijkstra
Dijkstra calculates the most efficient route in graphs with non-negative weights. It is the go-to choice for standard shortest path problems.

Real work

What teams actually run

Network Routing

Find the fastest way to move data packets through a series of weighted nodes.

Logistics Planning

Calculate the shortest distance for a vehicle traveling through a map of weighted intersections.

Game Development

Determine how non-player characters should navigate a grid using spatial heuristics.

Financial Modeling

Use Bellman-Ford to detect arbitrage opportunities or negative cycles in currency exchange graphs.

One connector, every AI

Shortest Path Engine works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Shortest Path Engine to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

760ms average. Fast in production.

Shortest Path Engine is checked daily against the live service.

Daily averagePeak 1001ms

Oct 3Today

Fastest day: 551ms
Slowest day: 1001ms
14-day trend: Stable+1%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 3 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Shortest Path Engine, so you can see the experience inside your AI.

It does not authenticate your account with Shortest Path Engine. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Shortest Path Engine Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_4jILbpr2C69ixKP1k3DHsnYznMAVua4uNkxoZ0qs/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Shortest Path Engine capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "shortest-path-engine-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_4jILbpr2C69ixKP1k3DHsnYznMAVua4uNkxoZ0qs/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Shortest Path Engine in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Shortest Path Engine owners hand off.

This MCP is built for anyone working with network topology, logistics, or mathematical modeling. You can hand off raw graph data to your agent to get immediate algorithmic results.

01
Data Scientists
They hand off graph datasets to verify pathing logic or test algorithm performance.
02
Logistics Engineers
They use the capabilities to find optimal delivery routes through weighted networks.
03
Software Developers
They offload complex graph math to the MCP instead of implementing algorithms from scratch.

FAQ

Questions Shortest Path Engine owners ask.

01
Can I use Dijkstra for graphs with negative weights?
No. Dijkstra is designed for graphs with non-negative weights. For graphs with negative weights, you should use the Bellman-Ford capability.
02
What makes A* different from Dijkstra?
A* uses spatial heuristics like Manhattan or Euclidean distance to find the path more efficiently than Dijkstra.
03
How do I use this with Claude or Cursor?
You connect to the Vinkius-hosted MCP once. After that, your agent in Claude, Cursor, or Windsurf will automatically see these capabilities as available functions.
04
Does this MCP handle directed graphs?
Yes. The engine can calculate paths for both directed and undirected weighted graphs.
05
Can it detect infinite loops?
Yes. The Bellman-Ford capability is specifically designed to detect negative cycles that would cause infinite cost-reduction loops.
06
When should I use the Dijkstra capability?
Use dijkstra when you are certain that all edge weights in your graph are zero or positive. It is highly efficient for standard shortest-path queries.
07
Can I use A* search without a heuristic?
The astar capability requires a valid heuristicType (either EUCLIDEAN or MANSDT) to guide its search. Without a spatial estimate, the algorithm cannot function as intended.
08
How does the engine handle negative edge weights?
For graphs with negative weights, you must use bellman_ford. This capability is specifically designed to process negative edges and identify if a negative cycle exists in your graph.

Explore

More in Algorithms

Connect Shortest Path Engine to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-03

Astar

Bellman ford

Dijkstra

What teams actually run

Network Routing

Logistics Planning

Game Development

Financial Modeling

Building your own app? The connector is yours to use.

Shortest Path Engine Connector

Claude Desktop

Data Scientists

Logistics Engineers

Software Developers

Can I use Dijkstra for graphs with negative weights?

What makes A* different from Dijkstra?

How do I use this with Claude or Cursor?

Does this MCP handle directed graphs?

Can it detect infinite loops?

When should I use the Dijkstra capability?

Can I use A* search without a heuristic?

How does the engine handle negative edge weights?

A* Pathfinder AI Connector

Graph Analysis Toolkit AI Connector

Hasura (Instant GraphQL & REST Engine) AI Connector

Causal-Graph Navigator AI Connector

Suggestions

Construction Schedule Critical Path Engine AI Connector

Ada Lovelace Algorithmic Prover AI Connector

Graph Coloring Scheduler AI Connector

JSON Path Query Engine AI Connector