Skip to main content
Glama
chrischall

honeybook-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

use_magic_link

Capture the signed-in HoneyBook client-portal session from an already open Chrome tab with ContextMint Bridge, using the magic-link URL only to identify the portal origin and save auth fields.

Instructions

Capture a HoneyBook client-portal session via the ContextMint Bridge browser extension. Prerequisites: install the ContextMint Bridge extension in Chrome (Safari isn't available yet), then open the vendor's magic-link URL in that browser so you're signed into their portal and leave that tab open. This tool then snapshots the auth fields out of the page's localStorage["HONEYBOOK_REACT_CURR_USER"] into ~/.honeybook-mcp/sessions.json. The tab only needs to be open and signed in — nothing is sniffed off a live request, so it does not matter whether the page is idle. All other tools use the most-recently-activated session by default. The magic_link_url arg is used only to derive the portalOrigin (cache key) — the tool does NOT open or navigate to it. For a QUESTIONNAIRE link (https://.hbportal.co/flow/?hash=…) use use_flow_link instead — that link writes a different, flow-scoped credential and this tool refuses it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
magic_link_urlYesFull magic-link URL from the vendor's HoneyBook email, e.g. https://<vendor>.hbportal.co/app/workspace_file/<id>/... Used only to derive the portal origin; you must already have this URL open in a Chrome tab with the ContextMint Bridge extension installed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.2
    • changedInput schema / properties / magic_link_url / description
      Previous value: -"Full magic-link URL from the vendor's HoneyBook email, e.g. https://<vendor>.hbportal.co/app/workspace_file/<id>/...  Used only to derive the portal origin; you must already have this URL open in a Chrome tab with the fetchproxy extension installed."New value: +"Full magic-link URL from the vendor's HoneyBook email, e.g. https://<vendor>.hbportal.co/app/workspace_file/<id>/...  Used only to derive the portal origin; you must already have this URL open in a Chrome tab with the ContextMint Bridge extension installed."
  2. Changed1 schema field changedv1.0.0
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  3. First observedv0.3.1

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the bare readOnlyHint=false annotation: it discloses that the URL is used ONLY to derive portalOrigin and is NOT navigated to, that nothing is sniffed off a live request, that it snapshots localStorage auth fields to a specific file, and that other tools default to the most-recently-activated session. This is rich behavioral context an agent needs to call it correctly.

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?

Purpose is front-loaded and each sentence carries information (prerequisites, storage target, idle-tab note, arg semantics, sibling routing). It is somewhat long and the portalOrigin explanation slightly overlaps the schema, but there is little wasted text.

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?

With no output schema and only one parameter, the description fully covers the effect (writes a session file), the default-session behavior governing sibling tools, and the routing rule away from use_flow_link. An agent has everything needed to invoke it correctly.

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 100% and the schema already notes the URL 'derives the portal origin', so baseline would be 3. The description adds real value by hammering that the tool does NOT open or navigate the URL and by tying the arg to a refusal condition for flow links, sharpening the parameter's non-obvious semantics.

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+resource ('Capture a HoneyBook client-portal session') plus the exact mechanism (ContextMint Bridge browser extension) and storage target (~/.honeybook-mcp/sessions.json). It explicitly names the sibling use_flow_link as the wrong tool for questionnaire links, so an agent can discriminate without opening either schema.

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?

Gives concrete prerequisites (install extension in Chrome, Safari unavailable, open the magic-link URL, keep the tab signed in), clarifies idle-vs-active is irrelevant, and states an explicit exclusion: questionnaire flow links must use use_flow_link, which this tool refuses. Nothing is left to inference.

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