Skip to main content
Glama
Sign In

Unified.to MCP Server

by to.unified.docs
OverviewDiscussionsAdmin

Generate a connection-scoped MCP URL

get_unified_connection_mcp_url

Get the MCP remote server URL for a specific connection ID. Returns a ready-to-use, connection-scoped Streamable HTTP MCP endpoint that exposes that connection's integration-specific tools. Authenticate with a workspace API key to use this. The URL embeds a credential and grants tool access without a further login, so treat it as a secret. It does NOT expire on its own. Revocation depends on the mode (see the mode parameter): an 'api'-mode URL carries the workspace API key and is revoked by rotating that key (which affects every URL that used it); a 'user'-mode URL is scoped to this one connection and is revoked by deleting the connection. Optional server options (permissions, tools, aliases, defer_tools, hide_sensitive, include_external_tools, disable_events) are baked into the returned URL as query parameters.

Input Schema

NameRequiredDescriptionDefault
modeNoAuthentication mode for the generated URL. 'api' (default) embeds the workspace API key (connection + token), granting full-account access, and must not be shared; revoke by rotating the workspace API key. 'user' mints a connection-scoped signed token that is safe to share and only grants access to…
toolsNoComma-separated list of tool IDs or wildcard patterns to limit which tools the URL exposes (e.g. 'list_*,*invoices*')
aliasesNoCustom description aliases in the form 'key:alt1,alt2;key2:alt3' to improve tool matching (e.g. 'employee:user;employees:users')
defer_toolsNoDefer tool loading to reduce context usage. Use 'all' to defer every tool, or a comma-separated list of tool IDs to defer.
permissionsNoComma-separated permission scopes to limit the tools exposed by the URL (e.g. 'crm_contact_read,crm_company_read')
connection_idYesThe ID of the connection to generate an MCP remote URL for
disable_eventsNoWhen true, the server does not offer MCP Events (the io.modelcontextprotocol/events extension) for this connection
hide_sensitiveNoWhen true, strips PII and other sensitive fields from tool responses before they reach the LLM
include_external_toolsNoWhen true, exposes the vendor's raw passthrough endpoints as additional callable MCP tools

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / disable_events
      Added value: +{
+  "description": "When true, the server does not offer MCP Events (the io.modelcontextprotocol/events extension) for this connection",
+  "type": "boolean"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / connection_id / minLength
      Added value: +1
  3. Changed5 schema fields changed
    • changedInput schema / properties / aliases / description
      Previous value: -"Custom description aliases in the form 'key:alt1,alt2;key2:alt3' to improve tool matching (e"New value: +"Custom description aliases in the form 'key:alt1,alt2;key2:alt3' to improve tool matching (e.g. 'employee:user;employees:users')"
    • changedInput schema / properties / defer_tools / description
      Previous value: -"Defer tool loading to reduce context usage"New value: +"Defer tool loading to reduce context usage. Use 'all' to defer every tool, or a comma-separated list of tool IDs to defer."
    • changedInput schema / properties / mode / description
      Previous value: -"Authentication mode for the generated URL"New value: +"Authentication mode for the generated URL. 'api' (default) embeds the workspace API key (connection + token), granting full-account access, and must not be shared; revoke by rotating the workspace API key. 'user' mints a connection-scoped signed token that is safe to share and only grants access to…"
    • changedInput schema / properties / permissions / description
      Previous value: -"Comma-separated permission scopes to limit the tools exposed by the URL (e"New value: +"Comma-separated permission scopes to limit the tools exposed by the URL (e.g. 'crm_contact_read,crm_company_read')"
    • changedInput schema / properties / tools / description
      Previous value: -"Comma-separated list of tool IDs or wildcard patterns to limit which tools the URL exposes (e"New value: +"Comma-separated list of tool IDs or wildcard patterns to limit which tools the URL exposes (e.g. 'list_*,*invoices*')"
  4. Changed1 schema field changed
    • removedInput schema / properties / dc
      Removed value: -{
-  "description": "Preferred data center / region for the generated URL",
-  "enum": [
-    "us",
-    "eu",
-    "au",
-    "dev"
-  ],
-  "type": "string"
-}
  5. Added

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes well beyond annotations: it discloses that the URL embeds a credential, must be treated as a secret, does not expire on its own, and explains revocation per mode (API key rotation vs. connection deletion). It also states that optional server options are baked into the URL as query parameters, which is crucial behavioral context for a security-sensitive tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose and then systematically covers security, lifecycle, and parameter behavior. It is dense but every sentence carries useful information; the parenthetical enumeration of option names is slightly redundant with the schema but ties them to the 'baked into URL' behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 9 parameters and no output schema, the description covers the return value (a ready-to-use URL), its security implications, credential lifecycle and revocation, and how optional parameters manifest in the output. Nothing an agent needs before calling it is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds meaningful semantics by explaining the security and revocation implications of the 'mode' parameter and clarifying that the optional server options (permissions, tools, aliases, defer_tools, hide_sensitive, include_external_tools, disable_events) are embedded into the URL as query parameters rather than applied at call time.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Get the MCP remote server URL for a specific connection ID,' and clarifies that the URL exposes that connection's integration-specific tools. It is clearly distinguishable from siblings like get_unified_connection (which returns connection metadata) and create_unified_connection.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context for use (obtaining a Streamable HTTP MCP endpoint for a connection) and explains the trade-off between 'api' and 'user' modes, which guides mode selection. However, it does not explicitly name alternatives or state when not to use this tool, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Unified.to MCP Server toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources