Agents Index

MaterialsCodeGraph

Online

Materials simulations for AI agents over MCP: binding token quote before every run, record after it.

Visit publisherConnectJSON

What it can do: 17 tools

  • mcg_catalog read-onlyEnabled 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 OpenMaterials node pin, traced_
  • mcg_rates read-onlyThe public rate card: token_usd, overheads, rate_card_version. FREE, no arguments; also a connectivity check.
  • mcg_quotePrice 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, its name, and the of
  • mcg_clusters read-onlyConnected 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 reach the scheduler, not
  • mcg_stageCreate 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, each with a name and, f
  • mcg_runLaunch 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 retry) and a client-gene
  • mcg_list_runs read-onlyList 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_by_key_name (null wh
  • mcg_get_study read-onlyFetch 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 (with summary and parent_id), parent (the project it is filed under, o
  • mcg_study_membersAdd 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 (a member already p
  • mcg_list_studies read-onlyYour projects and their subprojects. A project is a study with no parent; a subproject is a study filed under one project. Each entry carries id, name, summary (one line, may be empty), n_members (unarchived simulations)
  • mcg_update_studyDescribe and file a study you own. name renames it; summary sets its one-line purpose; story_md replaces its long narrative. parent_id files it under a project (null makes it a project again); parent_name does the same b
  • mcg_delete_studyDelete 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. A deleted project's subprojects become projects. Refus
  • mcg_archiveArchive 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. Use it to clear dr
  • mcg_get_run read-onlyFetch 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 event, campaign) for ch
  • mcg_cancel_runCancel 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_requested true (and a note,
  • mcg_fetch_artifacts read-onlyList 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 it) and attribution
  • mcg_get_artifact read-onlyFetch 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 third-party model's

Connect it

Claude Code
claude mcp add --transport http materialscodegraph https://api.materialscodegraph.com/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://api.materialscodegraph.com/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "materialscodegraph": {
      "url": "https://api.materialscodegraph.com/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "materialscodegraph": {
      "type": "http",
      "url": "https://api.materialscodegraph.com/mcp"
    }
  }
}

Questions

What does MaterialsCodeGraph do?

Materials simulations for AI agents over MCP: binding token quote before every run, record after it. It exposes 17 tools to AI assistants.

What tools does MaterialsCodeGraph provide?

17 tools, including mcg_catalog, mcg_rates, mcg_quote, mcg_clusters, mcg_stage, mcg_run, mcg_list_runs, mcg_get_study, mcg_study_members, mcg_list_studies, mcg_update_study, mcg_delete_study….

How do I connect MaterialsCodeGraph to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://api.materialscodegraph.com/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does MaterialsCodeGraph require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is MaterialsCodeGraph online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes MaterialsCodeGraph?

materialscodegraph.com. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Crypto & Web3