MaterialsCodeGraph MCP server

• Registry namecom.materialscodegraph/mcgverified in the MCP registry

The registry name sits under materialscodegraph.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-24
• Tools12
• Server calls itselfmcg
• Server version0.1.0
• Protocol version2025-06-18

On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 133 ms.

• Its tools do price a thermal conductivity calculation before running it, but not estimate cure degree of an epoxy after an isothermal hold.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP score67 of 100answers 100 · does the job 50 · definitions 96 · context 85 · connects 100 · lowered by the warning signs below
• What an agent can do with it1 of 2 use cases
• Answered100% of days11 of 11 daily checks
• Median first answer147 ms
• Space in an agent's context≈ 5,233 tokensthe definitions of all its tools (15), which an agent carries on every turn
• Tool definitionsA · 96 of 100
• Typed results0 of 15 toolsdeclared outputSchema: results come typed, read once

• Not saying whether it only reads or can destroy: 4 of 15

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• mcg_catalog

  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…

• mcg_rates

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

• mcg_quote

  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…

• mcg_clusters

  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…

• mcg_stage

  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…

• mcg_run

  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…

• mcg_list_runs

  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)…

• mcg_get_study

  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.

• mcg_get_run

  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…

• mcg_cancel_run

  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…

• mcg_fetch_artifacts

  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) and attribution on a third-party…

• mcg_get_artifact

  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 third-party model's file returns its…