Provides search over the TOTVS Protheus ERP knowledge base using vector similarity and reranking.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Protheus Chat MCP Server how to configure sales tax in Protheus?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP (Model Context Protocol) server that exposes a knowledge base search tool
for TOTVS Protheus ERP. Uses pgvector for vector similarity search,
OpenAI (text-embedding-3-small) for question embeddings, and
Cohere (rerank-v3.5) for result reranking.
git clone https://github.com/Straider2/protheus-mcp.git
cd protheus-mcp
cp .env.example .env
# edit .env with your credentials
uv pip install -e .
mcp-server-protheusOr run remotely via SSE:
{
"mcpServers": {
"protheus": {
"url": "https://mcp-protheus.yourdomain.com/sse"
}
}
}Related MCP server: mcp-rag-server
Variable | Default | Required |
|
| Database host |
|
| Database port |
| — | Database user |
| — | Database name |
| — | Database password |
| — | OpenAI API key (embeddings) |
| — | Cohere API key (reranking) |
Copy .env.example to .env and fill in your values.
uv pip install -e .
mcp-server-protheusAvailable commands:
mcp-server-protheus — stdio MCP server (Claude Desktop, Cursor)
mcp-server-protheus-sse — SSE/HTTP server (remote access)
protheus-mcp — alias for stdio
docker compose -f docker-compose.yml up -d protheus-mcp-sseThe server listens on http://localhost:8092/sse.
Add to claude_desktop_config.json:
{
"mcpServers": {
"protheus": {
"command": "uv",
"args": ["run", "mcp-server-protheus"]
}
}
}{
"mcpServers": {
"protheus": {
"url": "https://mcp-protheus.yourdomain.com/sse"
}
}
}protheus_search(question: str) — Search the Protheus FAQ knowledge base.
User Question → OpenAI Embedding → pgvector Cosine Search → Cohere Rerank → ResultsThe server connects read-only to PostgreSQL/pgvector.
uv run pytest tests/ -vAll tests use mocked connections — no real credentials needed.
protheus-mcp/
├── .env.example
├── pyproject.toml
├── README.md
├── src/protheus_mcp/
│ ├── __init__.py
│ ├── search.py # pgvector search + Cohere rerank
│ └── server.py # MCP server (stdio + SSE)
└── tests/
├── conftest.py
└── test_server.pyMIT
Search the Protheus FAQ knowledge base for answers about TOTVS Protheus ERP
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behavioral traits. It does not mention rate limits, pagination, result format, authentication needs, or any other behaviors beyond a basic search.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that effectively conveys the purpose. It is front-loaded and contains no superfluous words, though it could be slightly expanded without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple search tool with one parameter and an output schema, the description is minimally adequate. However, it lacks usage guidelines and behavioral details, leaving gaps for an agent to fully understand when and how to use it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has one required parameter 'question' with 0% description coverage, meaning the parameter itself has no description. The tool description adds no further meaning, such as examples, formatting, or expected question types.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches the Protheus FAQ knowledge base for answers about TOTVS Protheus ERP. It includes a specific verb ('Search') and resource ('Protheus FAQ knowledge base'), accurately conveying the tool's function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, nor are there any exclusions or context about appropriate usage scenarios. The description lacks any conditional instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0protheus_searchScored across 1 tool
With only one tool, there is no possibility of ambiguity or confusion between different tools.
A single tool enforces perfect naming consistency; there is no pattern to conflict.
One tool is borderline; for a FAQ knowledge base, a search tool alone may be insufficient for full interaction (e.g., retrieving full answers or browsing categories).
The tool covers search but lacks complementary operations like retrieving detailed results or listing topics, leaving notable gaps for a comprehensive FAQ toolset.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Token-free MCP server for structured RevoGrid Core, Pro, and Enterprise knowledge retrieval.
MCP server for querying Forkast documentation
