io.github.sypherinPublished by GitHub account sypherinv0.2.1Updated Oct 25, 2026
Ask the Altronis AI consultant, estimate AI cost (cloud vs own box), SG AI events, news. Read-only.
A read-only MCP server and CLI from Altronis, a Singapore AI consultancy, for asking its AI consultant, estimating AI costs, and pulling Singapore AI events, AI
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Follow the launch instructions in the repository.
MCP server and CLI for Altronis, the Singapore AI consultancy. It gives an AI agent (or you, from a shell) a set of read-only tools over the public altronis.sg endpoints: ask the Lyra consultant, estimate what AI would cost a team (cloud vs owning the hardware vs hybrid, in SGD), and pull Singapore AI events, news, and business-formation data.
One codebase, two entry points:
altronis-mcp: a stdio MCP server for Claude Desktop, Claude Code, Cursor, and any MCP client.altronis: the same tools as a command-line tool.Read-only by design: no tool mutates anything or captures leads.
Add it to your MCP client config. For Claude Desktop (claude_desktop_config.json):
For Claude Code:
Then ask your agent things like "use altronis to estimate what AI would cost a 35-person law firm, cloud vs its own server" or "what AI events are on in Singapore this month?".
Output is JSON on stdout; logs go to stderr.
MIT © Altronis (altronis.sg)
Source: README.md at commit 9294f3a
Ask Agent Lyra, Altronis's AI consultant, a question about applying AI in a Singapore business: our services, private/on-prem LLM deployment, AI governance (PDPA/MAS/MOH), SG AI grants, or build-vs-buy. Returns a short consultant-style answer. Use for open questions; use altronis_ai_cost_estimate when the question is what AI would cost or whether to own the hardware.
questionrequiredList upcoming AI events, meetups, and conferences in Singapore, curated by Altronis. Returns event title, date (SGT), venue, city, and a link. Use when someone asks what AI events are happening in Singapore.
limitLatest curated Singapore-relevant AI news headlines, aggregated by Altronis. Returns headline, source URL, and id. Use when someone asks for recent AI news in or affecting Singapore.
limitSingapore business-formation and industry-mix snapshot (from SingStat) that Altronis uses to frame the SG AI ecosystem: total new company formations and the top industries by formation count. Use for context on Singapore's business landscape.
Takes no parameters.
What Altronis offers: the six service pillars (agentic AI design & deployment, AI governance/risk/compliance, AI infrastructure & deployment incl. model optimization and training, AI product ownership, enterprise knowledge AI, AI rescue & remediation), engagement model, pricing shape, grants, and contact details. Static positioning info — no live call. Use to explain who Altronis is or how to engage them.
Takes no parameters.
Estimate the real monthly + multi-year cost of AI for a business, and whether to use the cloud, own a private on-prem box, or run the recommended hybrid (box + a lean cloud sub). Use WHENEVER someone asks what AI would cost, whether to buy their own hardware/server/GPU, 'own vs rent', 'is a private box worth it', how much per month/year, or 'what AI setup/hardware should we get'. Give the team as a MIX: power (all-day heavy/agentic), medium (daily bounded), light (occasional) — or pass an industry `preset` (see altronis_ai_cost_presets). Returns cloud cost (with a budget->frontier range), box capex + running cost, the hybrid monthly, the breakeven month, and a plain-English recommendation — all in SGD, on live model prices. Directional planning estimate, not a quote. Same engine as the calculator at altronis.sg/tools/tco.
modeplanlightmodelpowerbizMixmediumpresethorizonList the ~50 industry / company-type presets the Altronis AI cost calculator ships (id, name, sector, and default user mix). Call this when someone names an industry or company type but not a precise user breakdown, then pass the closest id to altronis_ai_cost_estimate as `preset`.
Takes no parameters.
90% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
npm install -g @altronis/altronis-mcp# or run without installing:npx @altronis/altronis-mcp --help{ "mcpServers": { "altronis": { "command": "npx", "args": ["-y", "@altronis/altronis-mcp"] } }}claude mcp add altronis -- npx -y @altronis/altronis-mcpaltronis ask "does an on-prem LLM satisfy PDPA?"altronis cost --preset law-firmaltronis cost '{"power":5,"medium":20,"light":15,"horizon":36}'altronis presetsaltronis events 5altronis news 5altronis ecosystemaltronis servicesaltronis tool altronis_ask '{"question":"..."}' # call any tool by namealtronis list # list all toolsnpm installnpm run build # tsc -> dist/npm test # unit tests (mocked fetch)npm run smoke # live integration test against altronis.sgnpm run drift # static facts + /mcp tool list still match the live sitenpm run dev # run the MCP server from source (tsx)npm run cli -- ask "..." # run the CLI from source