Skip to main content
Glama

Register MCP server

register_mcp_server
Destructive

Register an external MCP tool server for the organisation. Organisation admins only. Prefer a curated integration: call get_mcp_catalog and pass its adapter_key so the platform's read/write classification of the vendor's tools applies; omit adapter_key for a custom server. Remote URLs must be public http(s) endpoints (the SSRF policy refuses private and link-local addresses). Credential headers ride env as header-name to value entries; a sensitive-looking key (token, api_key, authorization, ...) REFUSES plaintext - the user must store the secret through the secret-slot flow and you pass the returned ${SECRET_SLOT:} sentinel as the value. Never ask the user to paste a secret into the conversation. New servers default to the read_only tier; tools become callable only after grant_mcp_tool.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>",
      "url": "<url>"
    },
    "name": "register_mcp_server"
  }
}

Input Schema

NameRequiredDescriptionDefault
envNoHeader-name to value entries sent on every request, e.g. {"Authorization": "${SECRET_SLOT:<id>}"}. Secret values must be ${SECRET_SLOT:<id>} markers; a ${VAULT:<path>} marker may only name one of this organisation's own secret slots.
urlYesThe MCP endpoint URL, e.g. 'https://mcp.sentry.dev/mcp'. Must be publicly reachable http(s).
nameYesUnique server name (max 120 chars, no '/' or whitespace), e.g. 'sentry'.
enabledNoWhether the server is active immediately (default true).
transportNoTransport protocol. Defaults to http (streamable HTTP); sse for legacy servers.
adapter_keyNoCurated adapter key from get_mcp_catalog (e.g. 'sentry', 'posthog', 'github', 'grafana', 'oneuptime'). Omit for a custom server.
descriptionNoWhat this server provides (max 2048 chars).
allowed_toolsNoRestrict the server to these tool names. Omit to allow the server's full inventory (grants still gate execution). The adapter's recommended_tools are a sensible starting set.
permission_tierNoread_only (default) offers only tools the platform classifies as reads; read_write also offers writes.
cluster_allow_listNoCluster UUIDs this server's tools may be used with. Omit for organisation-wide.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / env / description
      Previous value: -"Header-name to value entries sent on every request, e.g. {\"Authorization\": \"${SECRET_SLOT:<id>}\"}. Secret values must be ${SECRET_SLOT:<id>} or ${VAULT:<path>} markers."New value: +"Header-name to value entries sent on every request, e.g. {\"Authorization\": \"${SECRET_SLOT:<id>}\"}. Secret values must be ${SECRET_SLOT:<id>} markers; a ${VAULT:<path>} marker may only name one of this organisation's own secret slots."
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say it is a non-idempotent, destructive write; the description adds substantial context beyond that: admin-only authorization, an SSRF policy rejecting private/link-local URLs, the default read_only tier, and the grant gate before tools are callable.

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?

Front-loaded with the action and actor, then the preferred path, then security constraints. It is dense and nearly every clause carries a constraint, though the secret-handling passage is long enough that it slightly crowds the rest of the guidance.

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 10-parameter mutating tool with no output schema, the description covers authorization, safety policy, secret-handling protocol, tier defaults, and the required follow-up call. An agent has everything needed to invoke it without guessing or asking the user for a raw secret.

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 coverage is already 100%, so the baseline is 3. The description adds behavior not spelled out in the schema: sensitive-looking keys cause a REFUSAL rather than silent storage, secrets must go through the secret-slot flow, and the returned ${SECRET_SLOT:<id>} sentinel must be passed as the value. It stops short of covering parameters like transport, allowed_tools, or cluster_allow_list, which the schema handles alone.

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?

States a specific verb and resource ('Register an external MCP tool server for the organisation') plus the scope ('Organisation admins only'), which immediately distinguishes it from siblings like list_mcp_servers or set_mcp_server_enabled.

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

Usage Guidelines5/5

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

Explicitly routes the agent: prefer a curated integration via get_mcp_catalog and pass its adapter_key, omit adapter_key for a custom server, and the server's tools only become callable after grant_mcp_tool. Both the preferred path and the follow-up step are named.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.