Koskamo

Verbaterm Policy Intelligence MCP

Provides an MCP server for reviewing terms, privacy policies, and subscription language in plain English with source-backed citations. It offers a judged, citation-checked policy corpus accessible via streamable HTTP, supporting keyless public reads and API key access for AI tools.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Verbaterm Policy Intelligence MCP logo, by VerbatermCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by Verbaterm
MCP endpoint (Streamable HTTP)
https://verbaterm.com/mcp
Vendor documentation

What its tools do

7 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (7)

7 of 7 have a description · 0 of 7 declare behavior hints · 2 of 6 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Review terms and privacy policies in plain English
  • Access a citation-checked policy corpus
  • Search for specific clauses in legal documents
  • Get source-backed citations for policy changes

Source and maintenance

Community listingRegistry 1.0.0
mcp-registry: io.github.TensorsWillFlow/verbaterm@1.0.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
verbaterm 1.0.0
MCP protocol negotiated in check
2025-06-18
Tools
7 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Verbaterm: judged, citation-checked policy intelligence. Public corpus tools work keyless; start_private_review and ask_question need a Verbaterm API key and debit the caller plan. Hobby is $19/mo for 5k corpus credits. Mint a key: https://verbaterm.com/account#developer-api-keys. Skill: https://verbaterm.com/skill.md. Pricing: https://verbaterm.com/developers. Informational only — not legal advice.

Tools

7 advertised

search_policies
Advertised by the server during the last successful anonymous check.

Search Verbaterm's judged, citation-checked public policy corpus (companies, products, policy kinds). Returns derived review metadata — findings counts, scores, freshness — never raw policy text.

search_policies input schema
{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Company or product name to search."
    },
    "limit": {
      "type": "number",
      "description": "Max results (default 20, max 50)."
    },
    "category": {
      "type": "string",
      "description": "Optional audience category slug."
    }
  }
}
list_policies
Advertised by the server during the last successful anonymous check.

List published public-library policy reviews available in the corpus.

list_policies input schema
{
  "type": "object",
  "properties": {}
}
get_policy_review
Advertised by the server during the last successful anonymous check.

Get the full judged review for one published policy: findings with verbatim citation excerpts, scores, summary, and provenance. Cite the source URLs back to the user.

get_policy_review input schema
{
  "type": "object",
  "required": [
    "companySlug",
    "productSlug",
    "policyKind"
  ],
  "properties": {
    "policyKind": {
      "type": "string",
      "description": "terms, privacy, cookies, data_processing, or other."
    },
    "companySlug": {
      "type": "string"
    },
    "productSlug": {
      "type": "string"
    }
  }
}
start_private_review
Advertised by the server during the last successful anonymous check.

Start a private Verbaterm review of pasted policy text (requires a Verbaterm API key; debits the caller's plan allowance, not API credits). Returns a sessionId to poll with get_private_review_progress.

start_private_review input schema
{
  "type": "object",
  "required": [
    "policyText"
  ],
  "properties": {
    "policyKind": {
      "type": "string",
      "description": "terms, privacy, cookies, data_processing, other, or auto."
    },
    "policyText": {
      "type": "string",
      "description": "Full pasted policy text (min 80 chars)."
    },
    "documentTitle": {
      "type": "string"
    }
  }
}
get_private_review_progress
Advertised by the server during the last successful anonymous check.

Poll progress of a private review started with start_private_review.

get_private_review_progress input schema
{
  "type": "object",
  "required": [
    "sessionId"
  ],
  "properties": {
    "sessionId": {
      "type": "string"
    }
  }
}
get_private_review_result
Advertised by the server during the last successful anonymous check.

Get the completed private review (findings + citations) for a session started with start_private_review. Raw source text is not returned.

get_private_review_result input schema
{
  "type": "object",
  "required": [
    "sessionId"
  ],
  "properties": {
    "sessionId": {
      "type": "string"
    }
  }
}
ask_question
Advertised by the server during the last successful anonymous check.

Ask a citation-grounded follow-up question about a public library review or a private session (requires a Verbaterm API key; debits the caller's plan Q&A allowance).

ask_question input schema
{
  "type": "object",
  "required": [
    "question",
    "reviewRef"
  ],
  "properties": {
    "question": {
      "type": "string",
      "description": "3–1000 characters."
    },
    "reviewRef": {
      "type": "object",
      "description": "{ kind: \"public_path\", companySlug, productSlug, policyKind } or { kind: \"private\", sessionId }."
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
793 ms
95th percentile latency
793 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 793 ms · metadata changed · 7 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http verbaterm-policy-intelligence-mcp https://verbaterm.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add verbaterm-policy-intelligence-mcp --url https://verbaterm.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable verbaterm-policy-intelligence-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "verbaterm-policy-intelligence-mcp": {
      "url": "https://verbaterm.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "verbaterm-policy-intelligence-mcp": {
      "type": "streamableHttp",
      "url": "https://verbaterm.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start verbaterm-policy-intelligence-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "verbaterm-policy-intelligence-mcp": {
      "type": "http",
      "url": "https://verbaterm.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http verbaterm-policy-intelligence-mcp https://verbaterm.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://verbaterm.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "verbaterm-policy-intelligence-mcp": {
      "serverUrl": "https://verbaterm.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Verbaterm Policy Intelligence MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 1,293