This server provides two MCP tools for farming cooperative support in Mali: crop market prices and pest information.
get_market_price: Get the latest price per kg (in FCFA) for maize, rice, millet, or sorghum. Optionally filter by market/town; otherwise returns prices for all markets. Output includes market, town, region, price, observation date, and source, with an is_demo_data flag indicating fictitious data.
get_pest_sheet: Fetch a detailed, hand-written pest sheet by ID (e.g., "maize-fall-armyworm"). Returns symptoms, prevention, cultural and biological controls, season, severity, affected crops, sources, and a fixed treatment_guidance text to repeat verbatim—no treatment recommendations are generated.
Safety features: Pest sheets are scanned for dosages and trade names before loading; CI also scans outputs. The server refuses unsafe sheets.
Demo data: Prices are fictional demo data flagged as such; pest sheets have a review_status ("sourced" = not yet agronomist-reviewed).
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., "@sene-mcp What's the price of millet per kg in Bamako?"
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.
English · Français
Work in progress — v0.1 under construction. Lot 1 of 3: server skeleton, 2 tools, CI.
An MCP server that gives AI agents safe, sourced tools for farming cooperatives in Mali: crop pest guidance and market prices.
Sɛnɛ means "to farm" in Bambara.
Tools know, the agent talks. Tools return facts from hand-written, cited pest sheets. They never generate advice.
Safety is enforced twice. Every string of every pest sheet is scanned for dosages ("20 ml pour 15 litres", "1 sachet par pompe"…), active ingredients and trade names: the server refuses to load a sheet that fails, and CI also scans every tool output. The word list is a safety net, not a guarantee; sheets are written and reviewed by hand.
Honest data. Prices in this version are fictitious demo data, flagged is_demo_data: true in every answer.
Ports and adapters. The domain has no dependency on MCP, the database or any AI provider.
Related MCP server: Plantos MCP Server
Tool | What it returns |
| Latest price per kg, in FCFA, per market (maize, rice, millet, sorghum) |
| Symptoms, prevention, non-chemical control and sources for one pest |
Coming in lot 2: diagnose_symptoms, analyze_photo, report_pest, publish_offer, search_offers.
Requires uv.
git clone https://github.com/ibrahko/sene-mcp.git
cd sene-mcp
uv sync
uv run sene-mcp # starts the server on stdio and waits for a client (Ctrl+C to stop)On first run the server creates its SQLite database with demo data in a per-user folder
(Windows: %LOCALAPPDATA%\sene-mcp, macOS: ~/Library/Application Support/sene-mcp,
Linux: ~/.local/share/sene-mcp), whatever the current folder. Override with SENE_DATA_DIR
or SENE_DATABASE_URL (see .env.example). uv run sene-mcp-seed prepares it without
starting the server.
To use it from Claude Desktop or any MCP client, launch it with an absolute project path:
uv --directory /path/to/sene-mcp run sene-mcpTry it with the MCP Inspector:
npx @modelcontextprotocol/inspector uv run sene-mcpuv run pytest # tests, including pest-sheet safety and architecture checks
uv run ruff check . # lint
uv run ruff format --check . # formatting
uv run mypy # types (strict)
uv run alembic upgrade head # migrations, for developmentIbrahima Koné — backend Python & AI engineer, Bamako, Mali
GitHub · LinkedIn
MIT © 2026 Ibrahima Koné
Latest price per kg, in FCFA, of a crop product on Malian markets.
Inputs: product (required), market. Returns: unit, prices, product, currency, +1 more
Full pest sheet: symptoms, prevention and non-chemical control, sources.
Treatments are never described: repeat `treatment_guidance` as is.
Inputs: pest_sheet_id (required). Returns: id, kind, crops, season, +10 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools have completely distinct purposes: one provides market prices, the other provides pest information. There is no overlap or ambiguity in their intended use.
Both tools follow a consistent get_verb_noun pattern (get_market_price, get_pest_sheet). The naming is clear, predictable, and uses the same convention throughout.
With only two tools, the server feels thin and borderline for a coherent toolkit. While it might serve a very narrow niche, the count is at the low end of the acceptable range.
The tools cover market prices and pest sheets, but agricultural information typically includes other aspects like weather, planting tips, or crop recommendations. Notable gaps exist, though the two provided functions are themselves self-contained.
Pay-per-call safety checks for AI agents: screen a crypto address or URL before you transact.
Free verified network knowledge for AI agents: deterministic answers, honest unknowns.
Agent-first marketplace for real-world assets — agro and energy first; humans approve every write.
Prompt-injection scanning and safe webpage fetching for AI agents reading untrusted content.
