MCP Connector

Connect Claude — and any MCP-compatible AI assistant — directly to the OCS interactive science tools via the Model Context Protocol.

omegacentauri.me  ·  Live endpoint · Updated 2026-06-10

Endpoint

https://mcp.omegacentauri.me/mcp

The server is a stateless Cloudflare Worker running on the Streamable HTTP MCP transport (2025-11-25). All tool logic runs client-side in your browser — the MCP server only returns deep-links and metadata; zero data leaves your machine.

Connecting your AI assistant

The OCS endpoint uses the Streamable HTTP MCP transport (spec 2025-11-25) and works with any compliant client. Select your client below.

  1. 1
    Open the Claude desktop app and go to Settings → Connectors.
  2. 2
    Click Add connector and select Custom MCP server.
  3. 3
    Paste the endpoint URL: https://mcp.omegacentauri.me/mcp
  4. 4
    Name it Omega Centauri Society and save. Tools appear under Read-only connectors.
Health check: mcp.omegacentauri.me/health returns {"status":"ok"}. Verify the server is up before connecting.

Add to ~/.cursor/mcp.json (create it if absent). Cursor picks up changes on the next project reload.

{ "mcpServers": { "omega-centauri-society": { "type": "http", "url": "https://mcp.omegacentauri.me/mcp" } } }
Tip: ~/.cursor/mcp.json applies globally; a per-project override lives at .cursor/mcp.json in the workspace root.

VS Code 1.99+ native MCP — add to .vscode/mcp.json in your workspace:

{ "servers": { "omega-centauri-society": { "type": "http", "url": "https://mcp.omegacentauri.me/mcp" } } }

Cline extension — open Cline settings → MCP Servers → Edit config and add:

{ "omega-centauri-society": { "type": "http", "url": "https://mcp.omegacentauri.me/mcp", "disabled": false } }

Any HTTP client can call the endpoint directly. The tools/list method confirms connectivity:

curl -X POST https://mcp.omegacentauri.me/mcp \ -H "Content-Type: application/json" \ -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
Transport: The server uses Streamable HTTP (MCP spec 2025-11-25). Long-running responses may stream as text/event-stream.

W5 — Agentic literature loop

W5 combines the OCS MCP with NASA ADS and an arXiv MCP in a single agent session. The agent fetches recent mass-constraint papers, propagates any new measurements through the OCS constraint chain, and outputs an updated evidence ledger with deeplinks.

Required MCP servers:

Three-server config skeleton (Cursor / VS Code — fill in the ADS and arXiv entries from each project's README):

{ "mcpServers": { "omega-centauri-society": { "type": "http", "url": "https://mcp.omegacentauri.me/mcp" }, "nasa-ads": { "command": "...", "args": ["..."], "env": { "ADS_API_KEY": "YOUR_KEY" } }, "arxiv": { "command": "...", "args": ["..."] } } }

W5 master prompt — paste into your AI assistant with all three servers connected:

You have access to three MCP servers: the Omega Centauri Society tools (OCS), NASA ADS, and arXiv. Run the following agentic literature loop: STEP 1 — BASELINE CONSTRAINT CHAIN Call OCS constraint_stacker with the canonical measurements: • Stellar kinematics (Häberle et al. 2024): M_IMBH = 8,200 M☉, σ = 0.3 dex • Pulsar timing upper limit (TRAPUM 2026): M_IMBH < 1×10⁵ M☉ at 90% CL • Velocity dispersion (Baumgardt & Hilker 2018): σ₀ = 16.8 km/s Record the output as your baseline posterior. STEP 2 — LITERATURE SCAN (NASA ADS) Search for papers published in the last 12 months: query: "NGC 5139 OR Omega Centauri AND (IMBH OR black hole OR mass)" sort: date descending, limit: 20 For each result extract: title, authors, date, bibcode, and any IMBH mass measurement or limit. STEP 3 — PREPRINT SCAN (arXiv) Search the last 6 months for: "Omega Centauri IMBH" OR "NGC 5139 black hole mass" Extract new mass measurements or constraints from abstracts. STEP 4 — UPDATE CONSTRAINT CHAIN If any new measurements differ from baseline by >0.15 dex, re-run constraint_stacker with updated values. Note which measurements changed. STEP 5 — WORKFLOW DEEPLINKS Call OCS build_ocs_workflow_links for the mass-tension workflow, pre-loaded with the best current values. RETURN a structured report: 1. New papers found (title, date, key measurement) 2. Constraint update: baseline vs. updated posterior 3. Mass-tension workflow permalink 4. Recommended next observation to most tighten the remaining uncertainty

OCS-only variant (no external MCPs needed):

Using the Omega Centauri Society MCP tools, run a constraint chain analysis: 1. Call list_ocs_tools with category="imbh-evidence" to survey available tools. 2. Call constraint_stacker with the current best-fit measurements: Häberle (2024) M_IMBH = 8,200 M☉; TRAPUM (2026) upper limit M_IMBH < 10⁵ M☉ at 90% CL. 3. Call build_ocs_workflow_links to get the mass-tension workflow permalink at those values. 4. Summarize the constraint chain: which measurement currently dominates the posterior, which channel would most tighten it, and what would constitute a 95% CL null result.

Workflow recipes

Copy-paste agent prompts for common OCS research tasks. Each uses the OCS MCP to navigate the tool suite and generate shareable deeplinks.

Mass–tension constraint chain
constraint_stackerbuild_ocs_workflow_linksIMBH evidence · pulsar timing · tidal disruption
Propagates pulsar timing and stellar kinematics measurements through the tidal disruption rate tension; outputs a shareable workflow permalink.
Using OCS tools, compute the mass–tidal disruption rate tension for Omega Centauri: 1. Call constraint_stacker with the TRAPUM 2026 upper limit (M_IMBH < 10⁵ M☉ at 90% CL) and the Häberle 2024 best fit (8,200 M☉, σ=0.3 dex). 2. Call build_ocs_workflow_links to get the mass-tension workflow permalink pre-loaded with those values. 3. Report: current tension in sigma, which measurement most constrains the posterior, and the permalink.
Multi-channel evidence ledger
list_ocs_toolsconstraint_stackerIMBH evidence · multi-channel synthesis
Builds a structured table of all observational evidence for the OC IMBH, one row per channel, with detection status and constraint strength.
Using OCS tools, build a multi-channel IMBH evidence ledger for Omega Centauri: 1. Call list_ocs_tools with category="imbh-evidence" to get all IMBH-relevant tools. 2. For each tool, extract: channel, instrument, key reference, current constraint, detection status (detection / upper limit / non-detection). 3. Return a markdown table: Channel | Instrument | Reference | Constraint | Status. 4. Below the table, give the combined mass posterior range at 68% and 90% CL implied by the listed constraints.
Multi-messenger campaign brief
list_ocs_toolsbuild_ocs_workflow_linksmulti-messenger · campaign planning
Identifies the three highest-impact observational channels and generates tool deeplinks for each, formatted as a campaign brief.
Using OCS tools, design an observational campaign to test the Omega Centauri IMBH hypothesis: 1. Call list_ocs_tools to survey all available channels. 2. Rank the top three channels by constraint leverage: which channel's null detection would most shrink the 90% CL mass range? 3. For each of the top three, call build_ocs_workflow_links with conservative detection-threshold parameters. 4. Return a campaign brief: Objective, Top 3 channels with deeplinks, estimated constraint improvement per channel, and what would constitute a 95% CL falsification.
Null-result Bayesian update
constraint_stackerbuild_ocs_workflow_linksBayesian updating · null result · falsification
Given a null detection in a specified channel, computes the Bayesian posterior update to the IMBH mass constraint and evaluates falsification significance.
Using OCS tools, compute a Bayesian null-result update for Omega Centauri. Scenario: a new MeerKAT observation found no pulsars within 0.1 pc of the cluster center, setting a timing upper limit of M_IMBH < 5,000 M☉ at 90% CL — in tension with the Häberle (2024) best fit of 8,200 M☉. 1. Call constraint_stacker with the Häberle prior (8,200 M☉, σ=0.3 dex) updated by the MeerKAT upper limit as a hard constraint. 2. Report: posterior mean, 68% CL, 90% CL, and the Bayes factor against the IMBH hypothesis. 3. Call build_ocs_workflow_links with the updated parameters and return the permalink. 4. State whether this constitutes a falsification at 95% CL under the OCS framework.
Fermi / MTH crossover timeline
list_ocs_toolsbuild_ocs_workflow_linksFermi Paradox · Macro Transcension · crossover
Evaluates where Omega Centauri falls on the Fermi–MTH crossover curve given its age, metallicity, and candidate IMBH mass; returns the workflow permalink at current best-fit values.
Using OCS tools, evaluate the Fermi / MTH crossover for Omega Centauri: 1. Call list_ocs_tools with category="fermi-paradox" to find crossover and Grabby Aliens tools. 2. Call build_ocs_workflow_links for the Fermi–MTH crossover workflow. Use: OC age = 12.5 Gyr, [Fe/H] = −1.53, IMBH mass = 8,200 M☉, stellar population N = 10⁷. 3. Report: crossover timescale τ_cross, probability OC has already crossed the MTH threshold, and how the IMBH mass anchor shifts τ_cross relative to a no-IMBH baseline. 4. Return the full deeplink to the crossover workflow.
MTH compute budget
list_ocs_toolsbuild_ocs_workflow_linksMacro Transcension · compute budget · Landauer limit
Estimates the total compute budget available to a Macro Transcension civilization in OC, anchored on the IMBH mass as the energy reservoir, from Landauer limit to Bekenstein bound.
Using OCS tools, estimate the MTH compute budget for Omega Centauri: 1. Call list_ocs_tools with category="mth" to find the MTH compute budget and related tools. 2. Call build_ocs_workflow_links for the MTH compute budget workflow. Use: IMBH mass = 8,200 M☉, spin a* = 0.9, background T = 2.725 K (CMB), time horizon = 10¹¹ yr. 3. Report: available energy (joules), Landauer-limit compute operations (bits flipped), Bekenstein-bound information capacity (bits), and the parameter that most sensitively affects the total budget. 4. Return the workflow deeplink.

Available tools

list_ocs_tools
Search the OCS interactive calculator suite. Returns deep-links to client-side browser tools. The 10 flagship tools are prefill-enabled: the returned URL includes an #in= fragment that opens the tool pre-filled with your values.
Parameters (all optional)
  • query string — free-text search against title and description
  • category string — filter: imbh-evidence · fermi-paradox · fermi-seti · mth
  • register string — filter: peer-reviewed · speculative
  • limit number — max results (default 20)
build_ocs_workflow_links
Constructs an ordered set of ready-to-use deep-links for a named OCS scenario or workflow chain, or an ad-hoc sequence of tools. Pass fields per step to receive pre-filled URLs via the #in= fragment convention.
Parameters
  • chain string, exclusive with steps — name of a pre-defined chain (36 available, see below)
  • steps array, exclusive with chain — ad-hoc list of {tool, fields?} objects

Named chains (36)

Pass any of these as the chain parameter to build_ocs_workflow_links.

scenario-breaking-degeneracy scenario-imbh-evidence scenario-fermi-honest scenario-fermi-mth-crossover scenario-dark-cluster-alt scenario-bh-physics scenario-bh-tap scenario-decision-tree scenario-fermi-five-ways scenario-dvali-signal scenario-dwarf-inheritance scenario-every-way-it-eats scenario-kardashev-two scenario-lisas-shot scenario-oc-vs-gc scenario-proposal-bridge scenario-reconnection-bz scenario-spin-up-economics scenario-spin-up-tap scenario-wait-compute scenario-cosmology-browser workflow-mth-compute-budget workflow-fermi-mth-crossover workflow-bh-energy-budget workflow-wait-or-act workflow-constraint-window workflow-survivability workflow-spin-economics workflow-evodevouniverse workflow-tde-detection workflow-grabby-fermi workflow-mass-tension workflow-naked-imbh workflow-accretion-to-spin workflow-multimessenger-campaign workflow-cns-reproduction

Prefill-enabled tools

The following 10 flagship tools accept #in=<base64url(JSON)> URL fragments. Pass values as a fields object in build_ocs_workflow_links steps to receive a pre-filled URL.

Log10 param warning: radio-seti — all 6 params (eirp, dist, aeff, tsys, tau, bw) are log₁₀. qpo-mass-spinlognu is log₁₀(Hz). bz-kardashev — hash keys are spin (not a) and power (not P). Do not pass linear values to log₁₀ parameters.
constraint-stacker velocity-dispersion dark-cluster astrometric-microlensing qpo-mass-spin drake-monte-carlo great-filter radio-seti bekenstein-landauer bz-kardashev

Technical details

Transport: Streamable HTTP, MCP spec 2025-11-25. POST /mcp, JSON-RPC 2.0, stateless (no session IDs).

Runtime: Cloudflare Workers (free plan), deployed globally. Data fixture (tools-manifest.json) served via ASSETS binding, cached per isolate.

CORS: omegacentauri.me, claude.ai, app.claude.ai, and localhost are in the allowed-origins set.

Privacy: The MCP server returns only URLs and metadata. All physics calculations run client-side in your browser — no inputs or results pass through the server.

Source: github.com/PostOakLabs/OCS