Skip to main content
Glama
Kaushalendra-Marcus

evident

by Kaushalendra-Marcus
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
ANTHROPIC_API_KEYNoAPI key for Anthropic, required for extract() LLM-based schema extraction

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
fetchA

Fetch a URL through the resilience ladder (Tier 1 static -> Tier 2 rendered, escalating only when the failure mode suggests it'll help).

Args:
    url: The URL to fetch.
    mode: "markdown" returns clean readable content (default).
          "raw" also includes the raw HTML alongside the markdown.

Returns a JSON object with the extracted content plus `confidence`,
`method` (which tier/strategy produced it), and `tier` — always
check `confidence` before trusting the result for anything important.
On failure, `failure_reason` explains why (never a silent empty result).
extractA

Fetch a URL and extract structured fields matching a caller-supplied JSON schema, using an LLM — works on ANY site, not just ones with a dedicated recipe. Use list_recipes first if you suspect a faster, higher-confidence deterministic recipe already exists for this site.

Args:
    url: The URL to extract structured data from.
    json_schema: A JSON Schema (as a JSON string) describing the fields
        to extract, e.g. '{"type":"object","properties":{"price":
        {"type":"number"},"title":{"type":"string"}}}'.
    instructions: Optional extra guidance for the extraction model.

Requires ANTHROPIC_API_KEY to be set in the environment — this tool
will return a diagnosable failure (not a crash) if it isn't.
list_recipesA

List every registered extraction recipe (platform-specific, verified parsers — e.g. Greenhouse, Lever, Ashby job boards). Check this before calling extract with a manual schema: a matching recipe is faster and higher-confidence than LLM extraction.

use_recipeA

Invoke a specific recipe by id (see list_recipes) against one entity's slug/identifier on that platform.

Args:
    recipe_id: e.g. "ats_greenhouse", "ats_lever", "ats_ashby".
    slug: The platform-specific identifier (e.g. a Greenhouse board
        token — the part of boards.greenhouse.io/<slug>).
    entity_name: A human-readable name to attach to results (e.g. the
        company name), since the raw API responses often don't include it.
health_checkB

Proactively verify a recipe or a raw URL is still working, rather than discovering breakage only when a real search silently returns zero results. Pass either a recipe id (checks with a known-good test slug isn't available generically, so this reports whether the endpoint itself is reachable and returning the expected top-level shape) or a plain URL (runs it through the ladder and reports the outcome).

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
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

TDQS

A3.9/5.0

Scored across 5 tools

Disambiguation4/5

The tools mostly have distinct purposes: fetch grabs raw content, extract does structured LLM extraction, recipes are deterministic parsers, health_check verifies things. There's some boundary fuzziness between fetch and extract (both fetch a URL), and between extract and use_recipe (both produce structured data), but descriptions strongly clarify which to use when.

Naming Consistency4/5

Tools use consistent snake_case naming with imperative verbs (fetch, extract, list, use, health_check). 'list_recipes' and 'use_recipe' pair well, and 'health_check' is clear. Minor inconsistency: health_check is a compound noun rather than verb_noun, and 'extract'/'fetch' are bare verbs without object nouns, though still readable.

Tool Count5/5

Five tools is well-scoped for a web-scraping/extraction server. Each tool serves a distinct layer of the pipeline (fetching, LLM extraction, deterministic recipes, recipe invocation, health verification), with no redundant or padding tools.

Completeness4/5

The surface covers the full extraction lifecycle: discover recipes (list_recipes), use them (use_recipe), fall back to generic extraction (extract), basic fetching (fetch), and verification (health_check). Minor gap: no listing or discovery of available entities/boards beyond recipes, and no way to retrieve cached/past results, but the core workflow is complete.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources