Meridian Skills
Routes incoming tasks to LLM-generated candidates using a deterministic physics-inspired classifier. Each request sends your task to Llama-3.3-70B via GitHub Models' free tier, which emits candidate options. The local classifier then derives nine scalar features from each candidate's raw content,mass, scope, independence, cross-domain entropy, coherence,and assigns it a celestial body class (planet, moon, trojan, asteroid, comet, irregular) using fixed scoring rules. You get back a ranked list with full candidate bodies and decision rationale. Exposes one tool: route_task. Runs fully local via stdio or as a hosted HTTP endpoint with OAuth 2.1 for browser-based clients like Grok and ChatGPT. Useful when you need structured, deterministic routing logic on top of generative candidate lists without maintaining your own taxonomy.
- tool
- 1
- auth
- Secret needed
- transport
- STDIO
- env vars
- 3
- last updated
- May 2, 2026
Tools
1 toolsPublic tool metadata for what this MCP can expose to an agent.
route_taskSingle tool: route_task(task, limit?) — takes a natural-language task and returns ranked candidates with full bodies, classifications, and decision rules.
Single tool: route_task(task, limit?) — takes a natural-language task and returns ranked candidates with full bodies, classifications, and decision rules.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
MERIDIAN_API_URLdefault: https://ask-meridian.uk/api/orbital-routeOverride the backend router URL.
MERIDIAN_API_KEYsecretOptional bearer token for future rate-limit gating.
MERIDIAN_TIMEOUT_MSdefault: 90000Abort the fetch after this many ms.
Readme
Meridian MCP
Dynamic task routing via orbital mechanics. Domain-agnostic — candidates can be tools, prompts, documents, products, or any routable entity.
Per request, an LLM (Llama-3.3-70B via GitHub Models' free tier) emits N candidate routing entries. A deterministic classifier extracts a 9-scalar physics signature from each candidate's content alone — no curated lookup: mass (log-scaled body length × keyword count), scope, independence, cross_domain affinity (token-domain entropy across three star systems), fragmentation, drag, dep_ratio (max sibling Jaccard), lagrange_potential, coherence_time (g⁽¹⁾-style autocorrelation over the candidate's token stream — added in 3.1.0), plus orbital and optical parameters (semi-major axis, eccentricity, inclination, period, perihelion, aphelion, mean anomaly; wavelength, polarization, amplitude, phase). Six per-class scoring rules assign a celestial body class by argmax: planet, moon, trojan, asteroid, comet, or irregular.
The class-scoring rules:
Details
- Repository
- github.com/luuow/meridian-mcp
- Category
- AI & LLM Tools
- Package
meridian-skills-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Performance Co-Pilotmajor/pcp-mcpQuery system performance metrics via MCP - CPU, memory, disk I/O, network, processes0stars
AgentBillio.github.marketinglior-pixel/agentbill-mcpOne spend ceiling per agent job, as MCP tools. Bound to a task_ref you pass, not a calendar month.0stars
Domain Expertisemdfifty50-boop/domain-expertise-mcpInject deep domain knowledge into any AI agent0stars
Zero Core Budgetmeltingpixelsai/harvey-budgetAgent spending mgmt, budget tracking, ROI. Zero Core Budget.0stars
Agora402io.github.michu5696/agora402Escrow protection for agent payments on Base — USDC held in smart contract until job completion.0starsPaycrowio.github.michu5696/paycrowEscrow protection for agent payments on Base — USDC held in smart contract until job completion.0stars