MaterialsCodeGraph
com.materialscodegraph/mcgMaterials simulations for AI agents over MCP: binding token quote before every run, record after it.
Score: 100/100
Handshake verified by our own probe.
Tools · 15
Enabled simulation kinds (each with example mcg_quote arguments that price, a note naming what must exist first, or both; traced says whether the kind's default lineage has a single public OpenMateria…
The public rate card: token_usd, overheads, rate_card_version. FREE, no arguments; also a connectivity check.
Price a simulation. FREE: no hardware starts. Returns quote_id, quote_hash, tokens, rate_card_version, wall_s, expires_at, resource_class, resource_label and sku (the GPU class the quote is bound to, …
Connected clusters: id, name, preset (hive or auto), status (pending until the agent's first sync; connected; stale: the agent stopped syncing; revoked; scheduler_down: the agent syncs but cannot reac…
Create a DRAFT simulation whose input files are uploaded before pricing. FREE. Takes the same kind, spec, study, material and conditions as mcg_quote plus inputs: one entry per file the run needs, eac…
Launch the quoted simulation. SPENDS TOKENS: provisions hardware and bills the account. Requires the quote_id and quote_hash from mcg_quote (a stale hash or an expired quote REJECTS: re-quote and retr…
List runs, newest first: every run of this key's owner, or one quote's runs when quote_id is given. Returns at most limit rows (default 20, maximum 100). Each row carries state, spend_tokens, created_…
Fetch a study (the project a quote's `study` named) with its member simulations and their latest runs. Pass study_id or the exact name. Returns study, members (each with app_url) and app_url.
Add simulations to a study and remove them from it. You must own the study (get its id from mcg_get_study) and every listed simulation; a missing one is named and nothing changes. add appends in order…
Delete a study you own: the study and its membership list go. Its simulations, runs, artifacts and spend are untouched and stay reachable by id and in mcg_list_runs. Refused while the study has docume…
Archive or unarchive a simulation you own. Archiving hides it from the app's lists and studies; its runs, artifacts and spend are untouched, its direct link still opens, and archived false restores it…
Fetch a run's state, event timeline and LLM spend. The payload leads with a derived summary (state, current_stage, billing {quoted_tokens, charged_tokens, hold, policy}, fault, refusal, next, last eve…
Cancel a run from any non-terminal state before collecting (a collecting run's outputs are delivered and charged: 409). The cancel request is recorded immediately and returns run_id and cancel_request…
List a run's collected artifacts as a typed manifest: artifacts, a list of path, bytes, stage and sha256 per file, plus removed on a file the retention sweep deleted (its bytes are gone; do not fetch …
Fetch one artifact file's TEXT content, up to max_bytes (default 65536), with an explicit truncation note. Binary content REJECTS with unsupported_content; fetch binaries from the run's public page. A…
How to use
Claude Desktop or claude.ai: add a custom connector (Customize → Connectors; on Team and Enterprise plans an owner adds it under Organization settings → Connectors) with this server URL: https://api.materialscodegraph.com/mcp
Cursor or Cline: add to your MCP config:
{
"mcpServers": {
"materialscodegraph": {
"url": "https://api.materialscodegraph.com/mcp",
"transport": "streamable-http"
}
}
}