Skip to main content
Glama

Local MCP

by com.local-mcp
OverviewDiscussionsAdmin

Web Type

web_type
Destructive

Types text into a form field (input/textarea) or a rich-text editor (a contenteditable element) on the current page. target is a CSS selector or the field's visible label/placeholder. The field is read back after the page's own scripts run: if it ends up holding something else (a mask or an editor that rejected the text), the call fails with not_applied and returns the value the field holds. Does NOT submit — use web_click on the submit button afterwards (that step is gated). SPECIAL CASE — file inputs: if target resolves to an , text is instead treated as a LOCAL FILE PATH on this Mac and the file is attached (JS can't set a file input's value directly; this answers the native file panel programmatically without ever showing it).

Input Schema

NameRequiredDescriptionDefault
textYesThe text to type. For an input[type=file], this is instead the LOCAL FILE PATH to upload.
targetYesCSS selector or visible label/placeholder of the field.
confirmNoIgnored; kept for older clients.
sessionNoSession name (default 'default').

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / confirm / description
      Previous value: -"Must be true to type. Without it, returns a preview and types nothing."New value: +"Ignored; kept for older clients."
  2. Changed1 schema field changed
    • addedInput schema / properties / confirm
      Added value: +{
+  "description": "Must be true to type. Without it, returns a preview and types nothing.",
+  "type": "boolean"
+}
  3. Changed1 schema field changed
    • changedInput schema / properties / text / description
      Previous value: -"The text to type."New value: +"The text to type. For an input[type=file], this is instead the LOCAL FILE PATH to upload."
  4. Added

TDQS

A4.4/5.0
Behavior5/5

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

Far exceeds the annotations (which only say destructive/openWorld): it discloses the read-back verification after page scripts run, the specific `not_applied` failure mode plus the returned field value, and that submission is a separate gated step. The file-input special case explains a non-obvious mechanism (JS cannot set file inputs; the native panel is bypassed) that an agent could not infer from annotations.

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-loads the core action, then the verification behavior, then the no-submit rule, and finally the special case — a logical order with no filler. It is dense (parentheticals, caps, backticked codes) but each sentence carries distinct information.

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?

No output schema exists, yet the description explains what comes back on success and on failure (`not_applied` plus the field's actual value), and covers the edge case of file inputs. An agent has everything needed to call it and interpret the result.

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 coverage is 100%, so the schema already documents all four parameters including the file-path meaning of `text` and the ignored `confirm`. The description restates target and text semantics without adding format or syntax detail beyond the schema, so baseline 3 applies.

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 (type text into a form field / contenteditable editor on the current page) and scopes it precisely. It distinguishes itself from web_click (which performs the submit) and implicitly from ui_type by specifying the web-page context and CSS-selector/label targeting.

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?

Explicitly says 'Does NOT submit — use web_click on the submit button afterwards (that step is gated)', which is a clear when/when-not with a named alternative and a note that the follow-up is gated. It does not contrast with the sibling ui_type or state prerequisites such as needing a navigated page, so it falls short of a full 5.

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

All Local MCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources