Phalanx Server

v1.0.0

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
    "phalanx-server": {
      "url": "https://finalsub-6a65b318-seventie-amrita-university-coimbatore.app.nitrocloud.ai/mcp"
    }
  }
}

Connect remote tools directly via Claude's Web UI:

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.

Building an MCP server? Report issues and subscribe to updates here

Configure custom tools directly via ChatGPT's Web UI:

Icon (optional)

PNG only. Best results at 256 x 256 px or larger. Max file size: 10 KB

Name

Description (optional)

Connection

Authentication

Custom MCP servers introduce risk. Learn more

I understand and want to continue 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
    "phalanx-server": {
      "serverUrl": "https://finalsub-6a65b318-seventie-amrita-university-coimbatore.app.nitrocloud.ai/mcp"
    }
  }
}

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

[mcp_servers.phalanx-server]
url = "https://finalsub-6a65b318-seventie-amrita-university-coimbatore.app.nitrocloud.ai/mcp"

Connect directly using the Server-Sent Events endpoint:

https://finalsub-6a65b318-seventie-amrita-university-coimbatore.app.nitrocloud.ai/mcp

Available Tools

list_redaction_policies

List the available contract types and the redaction policy each one applies. Use this to populate a contract-type selector before redacting.

classify_document

Suggest a contract type from the document text. Advisory only — the user selection passed to redact_document always wins.

redact_document

Redact a contract under the policy for the selected contract type. Accepts a URL to a file (preferred) or raw text. Returns a structured JSON object (often stringified in the text field) containing the redacted text and a sessionId. YOU MUST parse this JSON to extract `sessionId` and `redactedText` to pass to build_graph.

restore_text

Decrypt the session token map and substitute original values back into text. For user-facing output only — never feed the result to a model.

destroy_session

Wipe the encrypted token map for a session. Call this after the final report has been delivered to the user.

build_graph

Build the clause knowledge graph from REDACTED contract text. Extracts clauses, categories, parties, and dependencies, then stores them in an in-memory graphology graph. Pass only redacted text — never the original document.

query_graph

Return the sub-graph for a set of clause categories, including 1-hop neighbours and attached entity nodes. Specialized risk agents use this instead of re-parsing text.

get_graph

Return the full serialized graph (nodes and edges) for a graph id.

get_clause_dependents

List clauses that reference or depend on a given clause. Use this before proposing a redline, to confirm the edit will not break a dependent definition elsewhere in the contract.

list_risk_agents

List the specialized risk agents and the clause categories each one queries from the graph.

analyze_corporate

Corporate Due-Diligence Agent. Queries entity, jurisdiction, assignment, and termination nodes to flag contracting-entity, governing-law, change-of-control, and termination-symmetry risks.

analyze_financial

Financial & Renewal Risk Agent. Queries payment, renewal, SLA, and audit nodes to flag payment-term, auto-renewal, pricing-escalation, and service-credit risks.

analyze_liability

Liability & Indemnification Agent. Queries liability, indemnity, and IP-ownership nodes to quantify worst-case exposure — caps, cap carve-outs, consequential-damage exclusions, and indemnity symmetry.

analyze_privacy

Privacy & Compliance Agent. Queries data-protection and confidentiality nodes to flag breach-notification gaps, missing regulatory framing, sub-processor discretion, and deletion obligations.

analyze_all_risks

Run all four specialized agents concurrently against the graph and return their merged findings, sorted most severe first. This is the normal entry point for a full analysis.

generate_redline

Redline & Counter-Proposal Synthesizer. Aggregates the specialized agents’ findings, drafts founder-friendly replacement clause language checked against the graph dependency edges, and produces a negotiation email. Set restore=true to decrypt the session token map and substitute original values back for the user — do not pass restored output to any model.

diff_clause

Render a unified-diff style comparison between the current clause language and a proposed replacement, for display in the results UI.

benchmark_clause

Benchmark a clause against standard benchmarks using TF-IDF cosine similarity

run_full_pipeline

Run the end-to-end Phalanx analysis pipeline. Accepts EITHER a URL to a PDF/Word file (preferred for file uploads), OR raw text. Parses, redact, builds the knowledge graph, runs all 4 risk agents, and synthesizes redlines in one call.

calculate

Perform basic arithmetic calculations

convert_temperature

Convert temperature units based on file content or direct input. Supports Celsius (C) and Fahrenheit (F).

tool_name