Skip to main content
Glama

Konexium

Server Details

Find and check companies across Africa: registries, sanctions lists and company websites, with every answer linked to its source. Anything that spends credits is proposed first and waits for your approval.

Ownership verified
Status
Healthy
Uptime
80.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A4.1/5.0

Scored across 2 tools

Disambiguation4/5

The two tools cover genuinely different phases: ask_konexium starts a request, answer_ask_approval resolves a human approval. The only friction is that 'answer_ask_approval' reads like answering an ask rather than an approval request, which could momentarily mislead an agent.

Naming Consistency3/5

Both names are snake_case and verb-led, but 'answer_ask_approval' is an awkward three-word compound that is not parallel to the service-anchored 'ask_konexium'. The pattern is readable but not cleanly predictable.

Tool Count3/5

Two tools is thin for a research service with threads, citations, and credit-based approvals; there is no way to list past asks or fetch a thread's history. The ask/approve pair earns its place, but the surface feels underspecified.

Completeness3/5

The core loop—ask, receive an approval_request, answer it—is covered, and declining is handled via approve:false. However, there is no retrieval of prior threads, listing of pending requests, or polling of asynchronous results beyond the approval response itself.

Available Tools

2 tools
answer_ask_approvalA
DestructiveIdempotent
Inspect

Answer an approval_request returned by ask_konexium. approve:false declines it: the proposed action is cancelled, nothing runs and no credits are spent; the result is the updated Ask response, in the same JSON shape as ask_konexium. approve:true runs nothing either, because an assistant cannot approve spending: it returns {status: "approve_in_konexium", approval_request_id, url, message}, and the person approves at that url. Answering a request that was already answered returns the earlier result.

Inputs: approve (required), approval_request_id (required).

ask_konexiumAInspect

Ask Konexium, a research service for African companies and markets, in plain language. It answers from company registers (GLEIF and national registries), sanctions and debarment lists, and the companies' own websites, and cites every source; what no source states is said plainly. Use it to check whether a company is real and active, screen it against sanctions lists, find companies that fit a brief, or watch a company for changes. Returns JSON {id, thread_id, status, output[]}. Each output item is a message (text with numbered [n] citations and their source URLs) or, when the request needs work that spends credits (a company search, a list check, monitoring or a data request), an approval_request with its id, label, credits and an approve_in_konexium link; status is then requires_approval. Nothing that spends credits runs until the person approves it in Konexium; to decline, call answer_ask_approval. Answers alone spend no credits but count toward the connection’s daily question limit.

Inputs: question (required), previous_response_id.

Tool Schema Changelog

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

Loading tool schema changelog…

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Remote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.
      16
      9 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Browse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources