Bruteforce Mcp

v0.1.0

A powerful MCP server built with NitroStack

Connection Setup

Add via Cursor Settings UI (Settings > Features > MCP > Add New MCP Server):

{
  "mcpServers": {
    // your other mcp servers
    "bruteforce-mcp": {
      "url": "https://bruteforce-1-6a5-bruteforce-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp"
    }
  }
}

Connect remote tools directly via Claude's Web UI:

Add custom connector BETA
Connect Claude to your data and tools. Learn more about connectors or get started with pre-built ones.
Advanced settings
Only use connectors from developers you trust. Anthropic does not control which tools developers make available and cannot verify that they will work as intended or that they won't change.

Configure custom tools directly via ChatGPT's Web UI:

New App
PNG only. Best results at 256 x 256 px or larger. Max file size: 10 KB
Custom MCP servers introduce risk. Learn more
OpenAI hasn't reviewed this MCP server. Attackers may attempt to steal your data or trick the model into taking unintended actions, including destroying data.

Add the following configuration block under mcpServers in your Antigravity configuration file (~/.gemini/config/mcp_config.json):

{
  "mcpServers": {
    // your other mcp servers
    "bruteforce-mcp": {
      "serverUrl": "https://bruteforce-1-6a5-bruteforce-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp"
    }
  }
}

Add the following configuration block to your Codex configuration file (~/.codex/config.toml):

[mcp_servers.bruteforce-mcp]
url = "https://bruteforce-1-6a5-bruteforce-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp"

Connect directly using the Server-Sent Events endpoint:

https://bruteforce-1-6a5-bruteforce-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp
Available Tools
hello_bruteforce

A simple health-check tool that confirms the BruteForce MCP server is running

resolve_entity

Deterministic entity resolution using blocking + Jaro-Winkler similarity. Returns scored matches with matched features. No LLM involved.

all_control_paths

Find all ownership paths between two entities via DFS traversal of owns_pct edges. Returns sourced evidence edges for each path. Deterministic, no LLM.

compute_control

Compute effective ownership control from a root entity to a target entity. Multiplies percentages along chains, sums parallel paths. Returns the ONLY source of on-screen percentages. Deterministic, no LLM.

find_shared_attributes

Find entities that share a common attribute (director, address, agent, phone) with the given entity. Used to pivot investigative modality when direct ownership paths are thin.

co_consignee_links

Find trade co-consignee relationships for a given entity. Determines which other entities share shipments with the target entity via bill-of-lading records.

score_evidence

Deterministically score evidence edges for confidence. Computes a weighted average of dataset quality, reliability tier, recency, completeness, and provenance. Returns the ONLY source of confidence numbers on screen.

match_sanctions

Deterministically match an entity against the loaded sanctions list. Uses Jaro-Winkler similarity on entity name against sanctioned names. Returns matches with scores and rationale.

assemble_dossier

Assemble a complete investigation dossier for a root-target pair. Combines control computation, evidence scoring, and sanctions matching into a single audit-ready report.