NudgeHost

Publish text as a link

share_text

Publish text at a public URL and get the link back. Accepts up to 2MB of content, measured in UTF-8 bytes. A filename ending in .html or .htm produces a page that renders live in the browser at its own nudgehost.site address. A .csv or .json file opens in NudgeHost's table or JSON viewer. A .md or .markdown file shows as formatted text, with headings, lists, tables, task lists and links, a Source view, a Copy source button and a raw text address; HTML inside it shows as typed and images are not loaded. Any other filename, including .txt, produces a page that shows the text as plain text, with a Copy text button and a raw text address. The link is public: anyone who has it can open the file without signing in.

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": {
      "filename": "<filename>",
      "content": "<content>"
    },
    "name": "share_text"
  }
}

Input Schema

Name	Required	Description	Default
`content`	Yes	The text to publish, exactly as it should be stored. For an .html filename this is the complete HTML document. May be empty.
`filename`	Yes	The name to give the file, including an extension. End it in .html or .htm to publish a web page, or .md to show Markdown as formatted text. Any other extension, apart from .csv and .json, shows the text as plain text. Up to 200 characters.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 16, 2026

changedInput schema / properties / filename / description

Previous value: -"The name to give the file, including an extension. End it in .html or .htm to publish a web page. Any other extension, apart from .csv and .json, shows the text as plain text. Up to 200 characters."New value: +"The name to give the file, including an extension. End it in .html or .htm to publish a web page, or .md to show Markdown as formatted text. Any other extension, apart from .csv and .json, shows the text as plain text. Up to 200 characters."

Changed1 schema field changedOct 14, 2026

changedInput schema / properties / filename / description

Previous value: -"The name to give the file, including an extension. End it in .html or .htm to publish a page the recipient can read in the browser. Up to 200 characters."New value: +"The name to give the file, including an extension. End it in .html or .htm to publish a web page. Any other extension, apart from .csv and .json, shows the text as plain text. Up to 200 characters."

First observedOct 14, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations only flag it as a non-read-only, open-world, non-destructive write. The description goes well beyond that: it discloses the 2MB UTF-8 byte cap, that the link is public and requires no sign-in, and how each extension is rendered (live HTML page, CSV/JSON viewer, Markdown with Source view, plain text fallback). This is exactly the contextual behavior an agent needs before publishing.

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 core action and outcome, then organized by extension rendering, then the public-access caveat. It is on the long side and the extension-to-page mapping partially restates the filename schema, but each sentence carries concrete detail rather than filler.

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 two-parameter write with no output schema, the description covers everything an agent must know: what it produces (a returned link), size limits, what each filename type yields, and the public visibility of the result. Little 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 coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema: extension-to-renderer mapping with specifics (.md shows formatted text, embedded HTML shown as typed, images not loaded), the byte-based size limit, and that the HTML filename expects a complete document.

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?

Opens with a concrete verb and outcome: 'Publish text at a public URL and get the link back.' The subject (text, published as a public link) naturally separates it from the upload-flow siblings create_upload_url and complete_upload, and from the read-only list_links.

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?

The description implies when to use it (you have text/a document and want a shareable link) but never says when to choose it over create_upload_url or complete_upload, nor any prerequisites or exclusion cases. Guidance is implied only, not stated.

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

All NudgeHost tools Inspect

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.