Skip to main content
Glama

Ghana Search: Ghana's Information Retrieval Engine

M8ven Score

Ghana Search is an information retrieval engine and Model Context Protocol (MCP) server that allows users, developers, and AI agents to search verified Ghanaian digital sources in real time.

Live search portal: https://search.ghanaopenai.org


Supported Sources

Ghana Search queries the public search APIs and pre-indexed databases of over 430 Ghanaian institutions and repositories, returning direct content URLs and downloadable PDFs rather than generic homepages:

  • Ghanaian Named Entity Definitions (104,000+ Concepts): Pre-indexed factual definitions from Ghana NLP covering national leaders, institutions, towns, traditional authorities, festivals, and cultural concepts, resolved in < 0.5ms offline and online.

  • Government Portals (164 websites): Direct search across ministries, departments, and agencies including the Ghana Revenue Authority (GRA), Food and Drugs Authority (FDA), Ghana Standards Authority (GSA), Ministry of Lands and Natural Resources, Lands Commission, and local assemblies.

  • District Assemblies (GhanaDistricts): News, development projects, and assembly reports across all 261 Ghanaian district assemblies.

  • Court Judgments and Legislation (GhaLII): Supreme Court, Court of Appeal, High Court rulings, Acts of Parliament, and Decrees with direct document and source download links.

  • Parliament of Ghana: Official parliamentary Bills, Hansard records, and committee reports with direct PDF downloads.

  • University Theses and Research: Academic research abstracts and direct PDF thesis download links from KNUST, University of Ghana (UGSpace), and University of Cape Coast (UCC).

  • National News Outlets: Real-time articles from B&FT Online, 3News, Citi Newsroom, Ghana News Agency (GNA), Yen.com.gh, The Chronicle, Ghana Business News, and Starr FM.

  • Ghana Yellow Pages & Commercial Directory (GhanaBusinessWeb): Direct search across verified Ghanaian commercial enterprises, pharmacies, hospitals, legal chambers, solar energy suppliers, hotels, and contractors with physical addresses, telephone contacts, and directory listings.

  • Ghanaian Reference: Scoped reference and historical background from Wikipedia (Ghana).


Related MCP server: Keepygaga RAG

Web Search Interface

Visit https://search.ghanaopenai.org to search directly from your browser:

  • Single Unified Search Box: Type any question, leader, institution, concept, place, product, or topic.

  • Multi-Source Synthesis: Returns matching Ghanaian Entity Definitions, Landmark Positioning Cards, Court Judgments, Research Theses, News Reports, and Business Contacts all in one feed.

  • Instant Category Filtering: Use on-the-fly filter chips (All Results, Entity Definitions, News & Media, University Theses, Laws & Government, Yellow Pages) to isolate specific sources without re-querying.

  • Title-First & Recent-First Ranking: Ensures high-signal exact matches and fresher articles are prioritized.


Querying the APIs

Ghana Search offers dedicated endpoints for each capability:

1. National Knowledge Retrieval (POST /api/search)

curl -X POST https://search.ghanaopenai.org/api/search \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Ghana Revenue Authority VAT and electronic invoicing requirements",
    "top_k": 5
  }'

2. Business Directory & Supplier Locator (POST /api/business/search)

curl -X POST https://search.ghanaopenai.org/api/business/search \
  -H "Content-Type: application/json" \
  -d '{
    "query": "tractor parts Accra",
    "top_k": 5
  }'

3. Landmark Location & Positioning (POST /api/location/lookup)

Descriptive positioning: returns which town/city, neighbourhood/suburb, and region a place is located in, and its main access road (no turn-by-turn navigation):

curl -X POST https://search.ghanaopenai.org/api/location/lookup \
  -H "Content-Type: application/json" \
  -d '{"landmark": "Ridge Hospital"}'
{
  "status": "success",
  "data": {
    "landmark": "Ridge Hospital",
    "found": true,
    "town": "Accra",
    "suburb": "North Ridge",
    "road": "Castle Road",
    "region": "Greater Accra Region",
    "description": "**Ridge Hospital** is located in North Ridge, Accra, Greater Accra Region. It is situated along or just off **Castle Road**."
  }
}

Request Parameters (POST /api/search)

Parameter

Type

Default

Description

text

string

Required

Your question or search topic

top_k

integer

50

Number of ranked results to return (max 500)

categories

list

Knowledge sources

Defaults to verified knowledge sources: ["news", "academic", "public_services", "wikipedia"]. Pass "business" explicitly to search Ghana Yellow Pages commercial directory.

Note: All search endpoints and external providers strictly enforce a hard 4.0-second timeout budget to guarantee rapid responses without hanging.


AI Inference Frameworks & Tool Calling (vLLM & SGLang)

Ghana Search is built natively for open-weights LLM inference runtimes (vLLM and SGLang). It provides standard OpenAI-compatible tool specifications and execution endpoints so models (such as Qwen 2.5, Llama 3.1/3.3, Mistral, Command R) can autonomously retrieve verified Ghanaian sources to ground their responses.

1. vLLM Tool Calling

Launch vLLM with auto tool calling enabled:

vllm serve Qwen/Qwen2.5-7B-Instruct \
  --enable-auto-tool-choice \
  --tool-call-parser hermes \
  --port 8000

Autonomous agent loop using the standard OpenAI client:

import requests
from openai import OpenAI

# Connect to local vLLM instance
client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")

# 1. Fetch OpenAI-compatible tool definitions from Ghana Search
tools = requests.get("https://search.ghanaopenai.org/api/tools").json()["tools"]

messages = [
    {
        "role": "user",
        "content": "What are the latest VAT invoicing requirements from the Ghana Revenue Authority?",
    }
]

# 2. Model decides to call ghana_search
response = client.chat.completions.create(
    model="Qwen/Qwen2.5-7B-Instruct",
    messages=messages,
    tools=tools,
    tool_choice="auto",
)

choice = response.choices[0]
if choice.message.tool_calls:
    tool_call = choice.message.tool_calls[0]
    messages.append(choice.message)

    # 3. Execute tool call via Ghana Search tool execution endpoint
    tool_result = requests.post(
        "https://search.ghanaopenai.org/api/tools/execute",
        json={
            "name": tool_call.function.name,
            "arguments": tool_call.function.arguments,  # Pass raw arguments directly
        },
    ).json()

    # 4. Feed grounded factual records back into conversation history
    messages.append({
        "role": "tool",
        "tool_call_id": tool_call.id,
        "content": tool_result["content"],
    })

    # 5. Generate final referenced answer
    final_response = client.chat.completions.create(
        model="Qwen/Qwen2.5-7B-Instruct",
        messages=messages,
    )
    print(final_response.choices[0].message.content)

2. SGLang Tool Calling

Launch SGLang server:

python3 -m sglang.launch_server \
  --model-path meta-llama/Llama-3.1-8B-Instruct \
  --port 30000

Autonomous agent execution with SGLang:

import requests
from openai import OpenAI

client = OpenAI(base_url="http://localhost:30000/v1", api_key="EMPTY")

# Fetch Ghana Search tool specifications
tools = requests.get("https://search.ghanaopenai.org/api/tools").json()["tools"]

messages = [
    {
        "role": "user",
        "content": "Find recent KNUST research on solar energy battery storage.",
    }
]

response = client.chat.completions.create(
    model="meta-llama/Llama-3.1-8B-Instruct",
    messages=messages,
    tools=tools,
)

if response.choices[0].message.tool_calls:
    call = response.choices[0].message.tool_calls[0]
    messages.append(response.choices[0].message)

    # Execute search
    res = requests.post(
        "https://search.ghanaopenai.org/api/tools/execute",
        json={"name": call.function.name, "arguments": call.function.arguments},
    ).json()

    messages.append({
        "role": "tool",
        "tool_call_id": call.id,
        "content": res["content"],
    })

    answer = client.chat.completions.create(
        model="meta-llama/Llama-3.1-8B-Instruct",
        messages=messages,
    )
    print(answer.choices[0].message.content)

3. Model Context Protocol (MCP) Remote Endpoint & Tools

Ghana Search provides three distinct, dedicated MCP tools:

MCP Tool Name

Functionality

Expected Input

Example Output

ghana_search

Verified national knowledge (gov, laws, theses, news)

Question or policy topic

Official acts, thesis abstracts, news reports

ghana_business_directory

Yellow pages & product supplier locator

Product, service, or business name

Matching businesses, locations, and phone numbers

ghana_location_info

Landmark positioning & access road

Place, facility, or landmark name

Town/city, suburb, and main access road

For MCP clients and agent orchestrators connecting over Server-Sent Events (SSE):

  • SSE Endpoint: https://search.ghanaopenai.org/mcp/sse

  • Tool Schema Endpoint: https://search.ghanaopenai.org/api/tools

  • Tool Execution Endpoint: https://search.ghanaopenai.org/api/tools/execute

  • Commercial Directory Endpoint: https://search.ghanaopenai.org/api/business/search

  • Location Lookup Endpoint: https://search.ghanaopenai.org/api/location/lookup


Offline-First Search & Domain Knowledge Packs

Ghana Search is built from the ground up for offline-first deployments. In rural communities, farming districts, remote clinics, and schools without reliable internet, local LLMs (running via vLLM, Ollama, SGLang, or llama.cpp) can query pre-built Domain Knowledge Packs with 0ms internet latency and zero network access.

1. Build a Custom Offline Knowledge Pack

You can generate a standalone SQLite knowledge pack from any question list, domain file, or Hugging Face dataset using the built-in pack builder CLI:

# Build an agricultural offline knowledge pack from Hugging Face:
python3 -m ghana_mcp.builder \
  --hf-dataset ghananlpcommunity/ghana-farmer-qa \
  --column question \
  --limit 500 \
  --output-db data/ghana_farmer_qa_pack.db \
  --export-jsonl data/ghana_farmer_qa_pack.jsonl

# Or build from a local text or CSV file of questions:
python3 -m ghana_mcp.builder \
  --queries-file my_health_questions.txt \
  --output-db data/ghana_health_pack.db

The builder runs each question through Ghana Search, retrieves matching publications, university theses, government circulars, and laws, and stores the full article content into a portable SQLite database.

2. Run Ghana Search in 100% Offline Mode

Launch the server completely air-gapped on localhost without internet access using the pre-bundled verified knowledge base:

# Launch server in offline mode (automatically uses pre-bundled knowledge packs)
python3 -m ghana_mcp.server --offline

# Or via environment variable with a custom domain pack
GHANA_SEARCH_OFFLINE=1 python3 -m ghana_mcp.server

# Connect directly to local LLMs via MCP stdio:
python3 -m ghana_mcp.server --stdio --offline

In offline mode:

  • 0 external network requests are performed.

  • Pre-bundled knowledge packs (covering agriculture, government regulations, court rulings, thesis research, and news) are auto-seeded on launch.

  • Queries are matched instantly (< 2ms) against the local knowledge pack using Title-First & Recent-First ranking.

  • All MCP tools, REST endpoints (/api/search), and tool execution APIs (/api/tools/execute) work seamlessly offline for local LLMs (vLLM, Ollama, SGLang, Claude Desktop).


Offline Corpus and Backup

All permanently cached documents (titles, body text, publication dates, direct PDF URLs, and source metadata) are continuously backed up to the Hugging Face dataset repository:


Organization

Ghana Search is developed and maintained by Ghana Open AI (https://ghanaopenai.org).

License

MIT License. See LICENSE for details.

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

    • F
      license
      Not graded
      quality
      D
      maintenance
      Exposes publisher journalism to LLMs and agent frameworks via search, retrieval, source grounding, and consistent citation, enabling accurate content retrieval with attribution and policy enforcement.
      -
    • A
      license
      A
      quality
      C
      maintenance
      Enables local-first hybrid knowledge retrieval from authorized Markdown and plain-text files, combining full-text and vector search with reranking and traceable source references via a single search tool.
      1
      MIT
    • F
      license
      Not graded
      quality
      C
      maintenance
      Provides AI agents and RAG pipelines with production-grade web search, deep research, news, academic, extraction, crawling, and source verification tools. Enables citation-anchored, deduplicated, fresh, and security-hardened evidence gathering from across the web.
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to perform LLM-optimized web searches, retrieve recent news articles with full text, and extract clean readable content from URLs. It returns synthesized answers, ranked cited sources, and page text suitable for grounding RAG workflows.
      296 npm
      MIT