mcg

endpoint

https://api.materialscodegraph.com/mcp

protocol

streamable-http ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is mcg live?

Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.

Is mcg free to use?

Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.

What tools does mcg have?

12 tools: mcg_rates, mcg_get_study, mcg_list_runs, mcg_catalog, mcg_clusters, mcg_quote, mcg_stage, mcg_run, ….

Is mcg safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• mcg_rates auth-required never probed

  The public rate card: token_usd, overheads, rate_card_version. FREE, no arguments; also a connectivity check.

  mcp-tool

  1234

  {
    "type": "object",
    "properties": {}
  }

  arguments 4 lines copy
• mcg_get_study auth-required 1h ago

  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.

  mcp-tool

  12345678910111213

  {
    "type": "object",
    "properties": {
      "name": {
        "type": "string",
        "description": "The exact study name given to mcg_quote or mcg_stage."
      },
      "study_id": {
        "type": "string",
        "description": "The study id."
      }
    }
  }

  arguments 13 lines copy
• mcg_list_runs auth-required never probed

  List runs, newest first: every run of this key's owner, or one quote's runs when quote_id is given. Each row carries state, spend_tokens, created_by_key_name (null when launched in the browser), study, headline (the AI brief's first line) and app_url. Returns runs.

  mcp-tool

  123456789

  {
    "type": "object",
    "properties": {
      "quote_id": {
        "type": "string",
        "description": "Optional: the quote_id (simulation) to list runs for."
      }
    }
  }

  arguments 9 lines copy
• mcg_catalog auth-required 1h ago

  Enabled simulation kinds (each with example mcg_quote arguments that price, or a note naming what must exist first; traced says whether the kind's default lineage has a single public OpenMaterials node pin, traced_note why or why not; research coordinators instead expose record_contract describing per-task completion requirements, not completed results), the costed lineage menu (runnability, physical conditions, indicative token costs and wall time per resource class, with its label and the offer SKU priced), the external-frontier graphs mcg_quote accepts, recipes (pass a recipe's quote object to mcg_quote unchanged), and codes (versions, licenses, pins; the software a run may execute, plus codes kept listed while their engines are withdrawn from sale). Call before mcg_quote. A kind or code absent here cannot run.

  mcp-tool

  1234

  {
    "type": "object",
    "properties": {}
  }

  arguments 4 lines copy
• mcg_clusters auth-required 1h ago

  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 reach the scheduler, nothing is offered; agent_outdated: an auto cluster's agent sends no inventory; snapshot_rejected: its last snapshot was over the size cap; snapshot_stale: no fresh capacity snapshot, nothing is offered; nodes_unavailable: none of an auto cluster's nodes accept jobs (drained, down, in maintenance or not responding), nothing is offered), status_detail (why, when not connected), classes (resource classes offered per partition, with per-job GPU, CPU and memory maxima and the GRES type), unclassified_gpus (GPU types present but not offered: type, count, reason), untyped_gpus, last sync time. Pass target {cluster_id} to mcg_quote to run there at zero hardware cost; only a connected cluster quotes. Clusters are created with POST /api/clusters (on the machine host with a spend-scoped key).

  mcp-tool

  1234

  {
    "type": "object",
    "properties": {}
  }

  arguments 4 lines copy
• mcg_quote auth-required never probed

  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, its name, and the offer SKU it priced; null when none was chosen), resource_options (one row per class the run can rent at this venue: resource_class, label, sku, tokens, wall_s, available; tokens and wall_s are what this quote would be on that class, null when it has no live offer now; re-quote with resource_class to pick one), the plan, and record: {traced: true, node, node_uid, map_version (the openmaterials graph version the node is pinned at; the commons map version is published at openmaterials.ai/data/version.json), material (the material the pinned conditions name: what the run computes)} when the completed run's OpenMaterials record is keyed on that public map node (measured instances cite the method that ran), else {traced: false, reason}. Research coordinators remain traced:false because they have no single public-node pin, but add record.record_contract: per-task omai completion requirements and the approved contract_sha256. Scientific tasks require simulation records; source-integrity QA requires node-less light_evidence, not scientific results. This is a required contract, not evidence that a run has completed; read it before you spend. The price is a binding ceiling: never more than this. mcg_run accepts only this quote_id with this quote_hash before expires_at and REJECTS a stale hash (quote_mismatch) or an expired quote (quote_expired). Arms, exactly one: kind from mcg_catalog (spec passed through verbatim, spec.params set the price, engine overrides the default only with a known engine id); external_frontier, an OpenMaterials external-solve envelope from mcg_catalog's graphs (also returns request_id, plan_digest and the compiled plan; an envelope not byte-equal to a supported graph REJECTS with unsupported_graph); draft_id (see the parameter). Also returns app_url, the owner's page in the app (for the human, never fetched by the agent) and, on the kind arm, warnings: the inputs the app cannot render without (material or structure_xyz, study); pass them. key_cap {tokens, daily_token_cap, message} appears when the quote alone is above this key's daily_token_cap: mcg_run with this key would be refused. accuracy_study needs no hardware_contract up front: the reply's contract_source says whether the run binds this simulation's published contract (published) or the labeled default synthetic one (default_synthetic).

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566

  {
    "type": "object",
    "required": [
      "name"
    ],
    "properties": {
      "kind": {
        "type": "string",
        "description": "Simulation kind from mcg_catalog, e.g. bulk_kappa."
      },
      "name": {
        "type": "string",
        "description": "A human label for the simulation."
      },
      "spec": {
        "type": "object",
        "description": "The spec object, e.g. {params: {...}, spec_yaml: '...'}. params drive the price. interface_tbc: params.production_steps and params.equilibration_steps set the NEMD budget (the run total across all interfaces) within the bounds the reply's certification.settable states (a refused run's summary.next names the key to raise); the price follows the budget."
      },
      "study": {
        "type": "string",
        "description": "The study (project) this simulation belongs to, by exact name; created if absent. Every quote for one investigation should name the same study so the app groups them together."
      },
      "engine": {
        "type": "string",
        "description": "Optional engine id override (rejected if unknown)."
      },
      "target": {
        "type": "object",
        "properties": {
          "cluster_id": {
            "type": "string"
          }
        },
        "description": "Run on one of your connected clusters (see mcg_clusters) instead of the cloud: hardware cost 0, gate fee per the rate card and plan, wall time includes the scheduler's queue-wait estimate. The cluster's status must be connected."
      },
      "draft_id": {
        "type": "string",
        "description": "Third arm: price a draft that mcg_stage created and whose inputs have been uploaded (refuses with inputs_missing while any declared input is absent). Also re-prices an already-quoted simulation, after its quote expired or to reproduce a run (pass the run's quote_id, its simulation_id): it clones the spec, the map pin and the staged inputs (not contract files, nor structure files the engine does not read; more than 25 inputs refuse) and returns the clone's fresh quote_id (reply carries requoted_from, and rerun_notes naming skipped inputs, structure overrides and an om_graph re-pin to the active bundle's graph snapshot). Mutually exclusive with every other argument but name, target and resource_class; a re-price keeps the quoted class on the same target unless resource_class names another."
      },
      "material": {
        "type": "string",
        "description": "Kind arm only: the material or formula being simulated (e.g. Si, MoS2). Also selects the reference structure. On a traced run whose engine fixes its own conditions it must match the spec's material."
      },
      "conditions": {
        "type": "object",
        "description": "Kind arm only: physical conditions as key/value pairs, e.g. {T: 300}. Values are numbers, strings or lists of up to 16 of them, except on an adapter engine, which runs them: there any value its conditions schema allows (lists, booleans, null) over the keys it declares, judged at quote. On a traced run whose engine fixes its own conditions, a key or value its record does not hold is refused; the error names what to send or omit."
      },
      "max_tokens": {
        "type": "integer",
        "minimum": 1,
        "description": "Graph arm only: quote-time hard ceiling; a quote above it REJECTS (never clamps)."
      },
      "structure_xyz": {
        "type": "string",
        "description": "Kind arm only: the simulated structure as extended-XYZ text; staged as the input structure.xyz so the app renders the exact geometry (takes precedence over the material reference)."
      },
      "resource_class": {
        "type": "string",
        "description": "The GPU class to run on, from a previous reply's resource_options (e.g. gpu-ampere-80). The quote prices that class only and the run rents only it: no fallback to another class, so it waits in quoted while the class has no capacity. Omit to price the cheapest class; the run may then take any class the engine runs on. A class the run cannot rent at this venue REJECTS with the allowed list."
      },
      "external_frontier": {
        "type": "object",
        "description": "The OpenMaterials #110 external-solve envelope, verbatim. Mutually exclusive with kind/spec/engine."
      }
    }
  }

  arguments 66 lines copy
• mcg_stage auth-required never probed

  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, each with a name and, for small text files, the text inline (staged immediately). Entries without text come back in uploads as presigned PUT URLs (valid 15 minutes, 4 GiB per file): upload each with a plain HTTP PUT of the file bytes, no key or header. Then call mcg_quote with draft_id to price; it REJECTS with inputs_missing until every declared input has arrived.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960

  {
    "type": "object",
    "required": [
      "kind",
      "name",
      "spec",
      "inputs"
    ],
    "properties": {
      "kind": {
        "type": "string",
        "description": "Simulation kind from mcg_catalog."
      },
      "name": {
        "type": "string",
        "description": "A human label for the simulation."
      },
      "spec": {
        "type": "object",
        "description": "The spec object; params drive the eventual price."
      },
      "study": {
        "type": "string",
        "description": "The study (project) this simulation joins, by exact name; created if absent."
      },
      "engine": {
        "type": "string",
        "description": "Optional engine id override."
      },
      "inputs": {
        "type": "array",
        "items": {
          "type": "object",
          "required": [
            "name"
          ],
          "properties": {
            "name": {
              "type": "string",
              "description": "Input file name (relative path, no leading slash)."
            },
            "text": {
              "type": "string",
              "description": "Small text content to stage inline; omit to receive an upload URL."
            }
          }
        },
        "minItems": 1,
        "description": "The input files the run needs."
      },
      "material": {
        "type": "string",
        "description": "The material or formula simulated."
      },
      "conditions": {
        "type": "object",
        "description": "Physical conditions: numbers, strings or lists of up to 16 of them (on an adapter engine, any value its conditions schema allows). On a traced run whose engine fixes its own conditions, a key or value its record does not hold is refused; the error names what to send or omit."
      }
    }
  }

  arguments 60 lines copy
• mcg_run auth-required never probed

  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 retry) and a client-generated idempotency_key (replaying it returns the existing run instead of launching twice). Optional max_tokens is a hard ceiling: a quote above it REJECTS the launch, never clamps. Returns run_id.

  mcp-tool

  123456789101112131415161718192021222324252627

  {
    "type": "object",
    "required": [
      "quote_id",
      "quote_hash",
      "idempotency_key"
    ],
    "properties": {
      "quote_id": {
        "type": "string",
        "description": "The quote_id returned by mcg_quote."
      },
      "max_tokens": {
        "type": "integer",
        "minimum": 1,
        "description": "Hard token ceiling: the launch is REJECTED if the quote exceeds it."
      },
      "quote_hash": {
        "type": "string",
        "description": "The quote_hash mcg_quote returned: proves the launch prices the exact quote the client saw."
      },
      "idempotency_key": {
        "type": "string",
        "description": "Client-generated key; retrying a launch with the same key must not double-charge."
      }
    }
  }

  arguments 27 lines copy
• mcg_get_run auth-required never probed

  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 event) for cheap polling, then app_url (the run page, for the human), study and headline. events holds the newest events that fit about 12 KB plus the last complete or fail event; events_omitted counts the others. In a payload over 2 KB, each value over 256 chars becomes {omitted_bytes, see}, where see names the route that returns the full event. A report body_md over 6,000 chars becomes the same stub; a brief body_md is cut at 6,000 chars and ends in an ellipsis; llm_spend.calls holds the newest 10 calls, and calls_omitted counts the rest. A done, node-addressed run also carries record (its OpenMaterials SimulationRecord), openmaterials_url (the datasheet link) and openmaterials_label: null, or the commons' note when the record cites a model, configuration or code that is not in the public registry (record.unregistered lists each model and configuration), so its values cannot be checked against the commons.

  mcp-tool

  123456789101112

  {
    "type": "object",
    "required": [
      "run_id"
    ],
    "properties": {
      "run_id": {
        "type": "string",
        "description": "The run id from mcg_run."
      }
    }
  }

  arguments 12 lines copy
• mcg_cancel_run auth-required never probed

  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_requested true; the platform kills the machine and terminalizes the run as state killed on its next orchestration tick (about 60 s). Poll mcg_get_run to observe the terminal state.

  mcp-tool

  123456789101112

  {
    "type": "object",
    "required": [
      "run_id"
    ],
    "properties": {
      "run_id": {
        "type": "string",
        "description": "The run id to cancel."
      }
    }
  }

  arguments 12 lines copy
• mcg_fetch_artifacts auth-required never probed

  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 it); truncated; source. Never returns file contents; fetch one file with mcg_get_artifact.

  mcp-tool

  123456789101112

  {
    "type": "object",
    "required": [
      "run_id"
    ],
    "properties": {
      "run_id": {
        "type": "string",
        "description": "The run id."
      }
    }
  }

  arguments 12 lines copy
• mcg_get_artifact auth-required never probed

  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.

  mcp-tool

  12345678910111213141516171819202122

  {
    "type": "object",
    "required": [
      "run_id",
      "path"
    ],
    "properties": {
      "path": {
        "type": "string",
        "description": "The artifact sub-path, e.g. results/report.md."
      },
      "run_id": {
        "type": "string",
        "description": "The run id."
      },
      "max_bytes": {
        "type": "integer",
        "minimum": 1,
        "description": "Max bytes to inline (default 65536)."
      }
    }
  }

  arguments 22 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.