Skip to main content
Glama

Server Details

A hosted MCP suite providing workflow primitives: web search, content fetching, compression, deduplication, cost/budget management, and agent memory pipelines.

Ownership verified

The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status
Unhealthy
Uptime
59.1% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
smartgate-network/smartgate-workflows
GitHub Stars
1
ChatGPT
–
Claude
–

TDQS

A4.2/5.0

Scored across 7 tools

Disambiguation5/5

Each tool has a clearly distinct role: budget management, context compression, semantic deduplication, URL fetching, memory, pipeline orchestration, and web search. Overlap between search/fetch and pipe/direct tools is explicitly addressed by the 'When to use'/'When NOT to use' guidance.

Naming Consistency5/5

All tools use a consistent smart_* snake_case prefix with descriptive nouns. The convention is predictable across the entire set.

Tool Count5/5

Seven tools is well-scoped for a context/research orchestration server. Each tool covers a distinct capability, and the pipeline tool composes rather than duplicates the others.

Completeness4/5

The surface covers the core lifecycle: budget tracking, search, fetch, deduplication, compression, memory, and multi-step pipelines. Minor gaps exist, such as explicit memory update and more budget management actions, but these are not fatal for the apparent domain.

Publisher details

Operator
SmartGate · Publisher source
Vendor relationship
First-party · Publisher source
Privacy policy
Not provided
Restrictions
Free tier available with API Key · Publisher source

Available Tools

7 tools
smart_budget_guardA
Read-only
Inspect

Purpose: Team token budget check, count, or usage record. When to use: action=check or count before expensive tools; action=record after token-consuming work. When NOT to use: General chat, reasoning, or as a substitute for the host model. Returns: JSON string with allowance, usage, or record confirmation. Composes with: before smart_fetch/smart_context_gate on large jobs. Omit team_id to use API key tenant.

Inputs: action (required), text, model, tokens, +4 more. Returns: result

smart_context_gateA
Read-only
Inspect

Purpose: Compress long prompts/context (LLMLingua) before the host LLM call. When to use: Context is too large for the model budget and text is already available. When NOT to use: Short messages or already small context. Optional purpose: Pass a short goal (step intent, user query) to pre-filter paragraphs by relevance before compression — e.g. "API rate limits", "pricing tables". Returns: JSON string with compressed text and ratio metadata. Composes with: downstream host LLM; often follows smart_fetch or smart_search.

Inputs: text (required), ratio, purpose. Returns: result

smart_dedupA
Read-only
Inspect

Purpose: Semantic deduplication across multiple text passages (SemHash). When to use: Several chunks or search results overlap heavily. When NOT to use: A single string or unrelated documents. Returns: JSON string with kept/removed indices or deduped texts. Composes with: after smart_search or before smart_context_gate.

Inputs: texts (required), threshold. Returns: result

smart_fetchA
Read-only
Inspect

Purpose: Fetch a public HTTP(S) URL and return Markdown-friendly content. When to use: The user provides a link and needs the page body or article text. When NOT to use: Full text is already in the conversation, or the target is not a fetchable URL. Returns: JSON string (parse it). Typically includes markdown or extracted text fields. Composes with: smart_context_gate after fetch for long pages; smart_search when no URL yet.

Inputs: url (required), timeout. Returns: result

smart_memoryAInspect

Purpose: Team-scoped long-term memory (add, search, get, delete). When to use: Persist or retrieve facts for this team/user across sessions. When NOT to use: World knowledge, one-off page content (use fetch/search), or global encyclopedic answers. Returns: JSON string; shape depends on action. Composes with: smart_search for grounding; smart_pipe template remember.

Inputs: action (required), text, query, top_k, +5 more. Returns: result

smart_pipeAInspect

Purpose: Run a multi-step pipeline (built-in template or custom steps). When to use: Several tools in sequence (e.g. research, read, remember). Templates: research, read, remember. When NOT to use: A single step — call the specific smart_* tool directly. Returns: JSON string with per-step results. Composes with: steps[].params (or legacy steps[].args) with tool = module or smart_* alias.

Inputs: url, text, query, steps, +1 more. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables web search, page fetching and cleaning, OCR from images, and broken-link checking through MCP tools, with multi-provider aggregation, caching, and anti-detection features.
      35 npm
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to perform unified web research through a single MCP server, including search, page fetching, recursive crawling, document parsing, YouTube transcript extraction, and deep multi-query research.
      3
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      A self-hosted MCP endpoint that gives AI agents unified web search, multi-hop deep research with real source citations, and page fetching/crawling. It automatically routes across free-tier providers and self-hosted fallbacks while tracking quotas and health, so agents just ask and never incur paid overage.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables agents to generate and index PDFs, search and cite document content, collect bounded public-web evidence, inspect OpenAPI contracts, and perform read-only Base chain queries through a hosted MCP service.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.