Skip to main content
Glama
marshall1727

clio-mcp

by marshall1727
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Generic Clio API v4 call

clio_api_request

Send GET, POST, or PATCH requests to Clio API v4 endpoints with OpenAPI validation; writes return a preview and require confirmation.

Instructions

Performs a GET, POST or PATCH on any Clio API v4 endpoint (path relative to /api/v4, e.g. '/matters' or '/matters/123'; or a full URL from meta.paging.next). DELETE is not allowed. The request is validated against the OpenAPI catalog (unknown path = error; unknown parameters = warning). For GET pass query.fields (without it the API returns only id and etag). The POST/PATCH body is automatically wrapped in {"data": ...}. Writes follow the preview → confirm handshake: the first call returns a preview with a confirmation token; repeat with confirm set to that token after the user approves.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyNoRequest body for POST/PATCH (the content of 'data')
pathYesPath relative to /api/v4 or a full URL
queryNoQuery parameters, e.g. {fields: 'id,display_number', limit: 50, order: 'id(asc)'}
methodYesHTTP method
confirmNoconfirm=true performs the write. Use it directly when the user's request contains everything needed; call without confirm (preview) only when you want to check the data first or something is unclear.
skip_validationNotrue = do not block the request because of validation errors (e.g. a new endpoint not in the catalog)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.0
    • changedInput schema / properties / confirm / description
      Previous value: -"Leave out on the first call: the tool returns a PREVIEW with a confirmation token. Show the preview to the user, wait for their explicit approval, then repeat the call with identical arguments and confirm set to that token. confirm=true is not accepted."New value: +"confirm=true performs the write. Use it directly when the user's request contains everything needed; call without confirm (preview) only when you want to check the data first or something is unclear."
  2. First observedv1.0.0-beta.1

TDQS

A4.1/5.0
Behavior5/5

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

No annotations, so the description carries the full burden and does so: it discloses the DELETE prohibition, catalog validation semantics (unknown path=error, unknown params=warning), the auto-wrapping of bodies in {"data": ...}, the preview→confirm handshake with token semantics, and the GET field-default behavior. These are non-obvious traits an agent could not infer from schema alone.

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?

Four dense sentences, each adding non-redundant information, with the method/scope statement front-loaded. Slightly overstuffed but no filler.

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

Completeness4/5

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

For a generic dispatcher with no output schema and no annotations, the description covers method restrictions, validation, body wrapping, field selection, and the write-confirmation protocol. It could still note failure modes (rate limits, auth) but is comfortably sufficient to call correctly.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents each parameter, setting the baseline at 3. The description adds some real value (path is relative to /api/v4 or a full next-page URL; GET requires query.fields; body is wrapped in data), but does not re-explain method enum or confirm beyond what the schema says.

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 (performs GET/POST/PATCH) and resource (any Clio API v4 endpoint), plus the excluded method (DELETE). It distinguishes itself from siblings because it is the explicit escape hatch for arbitrary endpoints when no dedicated tool (e.g. clio_matter_get) fits.

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

Usage Guidelines3/5

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

Gives concrete operating constraints (no DELETE, validation against catalog, GET needs query.fields, writes need preview→confirm) but never says when to prefer this generic tool over the dozens of dedicated siblings like clio_matter_create or clio_contact_update. Routing guidance is implied, not stated.

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

Deploy Server

Other Tools