Skip to content

MaterialsCodeGraph MCP server

com.materialscodegraph/mcgmaterialscodegraph.comstreamable-httpv0.1.1Scanned

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

15 tools: 3 can delete or cancel things, 7 change things and 5 only read.

Tools: 3 delete, 0 irreversible, 7 write, 5 read.
  • Reads private data · 2
  • Reads text others write · 0
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

3 tools here can delete or cancel things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the MaterialsCodeGraph MCP server can do

The MaterialsCodeGraph MCP server is published by materialscodegraph.com, a domain the MCP Registry verified. It has 15 tools. It can delete or cancel things (3 tools: mcg_delete_study, mcg_archive and mcg_cancel_run) and create or change data (7 tools: mcg_catalog, mcg_rates, mcg_quote, mcg_clusters and 3 more). 5 tools only read.

2 tools read private data (mcg_fetch_artifacts and mcg_get_artifact).

The fixed checks matched 2 findings (long-description and annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 10, 2026, version 0.1.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

15 tools

Deletes or cancels 3Claude Code: deny
  • mcg_archiveArchive or unarchive a simulation you own.1 finding

    Why it is in this group

    • The name "mcg_archive" says "archive": a word for removing or ending something.
    • The server marks it not destructive (destructiveHint: false), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "mcg_archive" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".

      Matched text

      annotations: {"destructiveHint":false,"idempotentHint":true}; The name "mcg_archive" says "archive": a word for removing or ending something.

      What this check looks for
    Description, as the server wrote it
    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. Use it to clear drafts that never ran (they cannot be deleted once quoted). Returns simulation_id, archived, archived_at (null when unarchived) and app_url.

    Annotations the server declares

    • idempotentHint: true
    • destructiveHint: false
  • mcg_cancel_runCancel a run from any non-terminal state before collecting (a collecting run's outputs are delivered and charged: 409).No findings

    Why it is in this group

    • The name "mcg_cancel_run" says "cancel": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    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 (and a note, for a running campaign); the platform kills the machine and terminalizes the run as state killed on its next orchestration tick (about 60 s). A running campaign's cancel takes several ticks (a tick is about 60 s), 3 or more while children are open: the parent winds down, its open children are cancelled (a collecting child finishes and counts), then settlement charges the done children's measured tokens and releases the rest of the hold. Poll mcg_get_run to observe the terminal state.

    Annotations the server declares

    • destructiveHint: true
  • mcg_delete_studyDelete a study you own: the study and its membership list go.No findings

    Why it is in this group

    • The name "mcg_delete_study" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    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 documents or a live public link (remove those in the app first). Returns study_id, deleted true and former_member_ids, enough to rebuild it.

    Annotations the server declares

    • destructiveHint: true
Changes things 7Claude Code: ask
  • mcg_catalogEnabled 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 singl…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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 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 (each with the envelope to pass as external_frontier), recipes (pass a recipe's quote object to mcg_quote unchanged), and codes (versions, licenses, pins; the only software a run may execute). Call before mcg_quote. A kind or code absent here cannot run.

    Annotations the server declares

    • readOnlyHint: true
  • mcg_clustersConnected 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 s…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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, the GRES type, and in_use: false when no engine runs on the class), 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).

    Annotations the server declares

    • readOnlyHint: true
  • mcg_quotePrice a simulation.1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    Findings

    • Info

      The description is 3,548 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...lone is above this key's daily_token_cap: mcg_run with this key would be refused."

      What this check looks for
    Description, as the server wrote it
    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), pricing {hours_factor, potential_cost_ratio, note} when a potential staged at slots/potential was priced by its predicted per-step cost over the default's (the hours, the wall time and the run's wall limit are multiplied by hours_factor, at least 1, the factor on the quote's resource_class: each resource_options row is priced at its own class's factor; the per-second rate is unchanged), 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), potential {label, sha256} when the run's staged potential is not NEP89} 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}, which only the graph arm, research coordinators and the untraced preview kinds (the reason is the kind's traced_note) return: a kind-arm spec no record can name is refused with the reason, and one naming several materials or interfaces carries detail.split: one {material, spec} per simulation, each ready to quote (pass the same study to group them). 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. A quote with billing.policy metered_v1 (D-083) carries billing {billing_mode, rate_tokens_per_s, boot_tokens, gate_tokens_per_stage, laws, liability_table, waiver_remaining_today, statement, dispute}: a metered run pays the lower of its work and its time, and a refusal the liability table names as the caller's, after the code computed, pays its work, never more than the quote. 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.
  • mcg_ratesThe public rate card: token_usd, overheads, rate_card_version.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    The public rate card: token_usd, overheads, rate_card_version. FREE, no arguments; also a connectivity check.

    Annotations the server declares

    • readOnlyHint: true
  • mcg_runLaunch the quoted simulation.No findings

    Why it is in this group

    • The name "mcg_run" says "run": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • idempotentHint: false
  • mcg_stageCreate a DRAFT simulation whose input files are uploaded before pricing.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    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.
  • mcg_study_membersAdd simulations to a study and remove them from it.No findings

    Why it is in this group

    • The description's first verb is "add": a word for a change.
    Description, as the server wrote it
    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 (a member already present keeps its place); remove takes a simulation out of this study only, and the simulation and its runs are untouched. Joining a public study is refused for a run that cannot be public. Any change takes an auto-grouped study out of auto-grouping. Returns study, added, removed (the ids that changed), member_simulation_ids (unarchived members, in order), archived_member_ids and app_url.

    Annotations the server declares

    • idempotentHint: true
Only reads 5Show 5 read-only tools
  • mcg_fetch_artifactsList 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…Reads private dataNo findings

    Why it is in this group

    • The name "mcg_fetch_artifacts" says "fetch": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "list" and "file": it reads files.
    Description, as the server wrote it
    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 model's file (its license notice; keep it with any copy); truncated; source. Never returns file contents; fetch one file with mcg_get_artifact.

    Annotations the server declares

    • readOnlyHint: true
  • mcg_get_artifactFetch one artifact file's TEXT content, up to max_bytes (default 65536), with an explicit truncation note.Reads private dataNo findings

    Why it is in this group

    • The name "mcg_get_artifact" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "fetch" and "file": it reads files.
    Description, as the server wrote it
    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 full license notice first, as an [attribution] text item.

    Annotations the server declares

    • readOnlyHint: true
  • mcg_get_runFetch a run's state, event timeline and LLM spend.No findings

    Why it is in this group

    • The name "mcg_get_run" says "get": a word for reading.
    Description, as the server wrote 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 event, campaign) 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. A campaign parent's summary.campaign holds its round, step, ceiling_tokens, committed_tokens, measured_tokens, finish, counts (children per state), children (every open child and the newest 8 settled ones, each with run_id) and children_omitted; GET /api/runs/:id lists every child. Its children are charged in the parent's one capture, so a child shows charged_tokens 0 and hold parent.

    Annotations the server declares

    • readOnlyHint: true
  • mcg_get_studyFetch a study (the project a quote's `study` named) with its member simulations and their latest runs.No findings

    Why it is in this group

    • The name "mcg_get_study" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
  • mcg_list_runsList runs, newest first: every run of this key's owner, or one quote's runs when quote_id is given.No findings

    Why it is in this group

    • The name "mcg_list_runs" says "list": a word for reading.
    Description, as the server wrote it
    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_by_key_name (null when launched in the browser), study, headline (the AI brief's first line) and app_url. Returns runs and next_before: pass next_before as before to get the next older page; it is null on the last page.

    Annotations the server declares

    • readOnlyHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:42 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
11
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 11 tools that change things (3 destructive, 8 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.materialscodegraph.com/mcp: tools/list returned 17 tools to an anonymous client, including mcg_delete_study (destructive), mcg_archive (destructive), mcg_cancel_run (destructive), mcg_catalog (write), mcg_rates (write) and 6 more

    What this check looks for

Posture changes

  1. Nov 13, 2026
    • Tools that change things, listed without credentials: 10 to 11
  2. Nov 6, 2026
    • Tools that change things, listed without credentials: 7 to 10

Findings

Matches of fixed checks, with the text they matched.

1 warn1 info
  • The server marks "mcg_archive" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".

    Matched text

    annotations: {"destructiveHint":false,"idempotentHint":true}; The name "mcg_archive" says "archive": a word for removing or ending something.

    What this check looks for
  • The description is 3,548 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...lone is above this key's daily_token_cap: mcg_run with this key would be refused."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. Tools that change things, listed without credentials: 10 -> 11.View diff
    • Tools that change things, listed without credentials: 10 to 11
  2. Tools3 added, 3 changed.+3 added~3 changedView diff
  3. PostureRemote posture changed. Tools that change things, listed without credentials: 7 -> 10.View diff
    • Tools that change things, listed without credentials: 7 to 10
  4. Tools9 changed.~9 changedView diff

Install

Pinned to version 0.1.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http mcg https://api.materialscodegraph.com/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http mcg https://api.materialscodegraph.com/mcp --header 'Authorization: <your-authorization>'

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__mcg__mcg_list_runs",
      "mcp__mcg__mcg_get_study",
      "mcp__mcg__mcg_get_run",
      "mcp__mcg__mcg_fetch_artifacts",
      "mcp__mcg__mcg_get_artifact"
    ],
    "ask": [
      "mcp__mcg__mcg_catalog",
      "mcp__mcg__mcg_rates",
      "mcp__mcg__mcg_quote",
      "mcp__mcg__mcg_clusters",
      "mcp__mcg__mcg_stage",
      "mcp__mcg__mcg_run",
      "mcp__mcg__mcg_study_members"
    ],
    "deny": [
      "mcp__mcg__mcg_delete_study",
      "mcp__mcg__mcg_archive",
      "mcp__mcg__mcg_cancel_run"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as mcg. Review it before you use it.

Capability tags behind 2 rules
  • mcp__mcg__mcg_fetch_artifacts private-data
  • mcp__mcg__mcg_get_artifact private-data

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.materialscodegraph/mcg/verify?hash=ef978d7ca39c3cbb321e9fa385104c5126a04b9b50a5097467275b60821484a6" | jq -e '.changed == false'

Pinned hash ef978d7ca39c, from Nov 10, 2026, 20:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.materialscodegraph/mcg/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.materialscodegraph/mcg
[![Anlyon Radar](https://radar.anlyon.com/badge/com.materialscodegraph/mcg.svg)](https://radar.anlyon.com/servers/com.materialscodegraph/mcg)

Source: MCP Registry · repository. Synced Oct 21, 2026, 17:58 UTC.

MaterialsCodeGraph MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the MaterialsCodeGraph MCP server safe?

No scan can promise that. What its definitions show: 15 tools, 10 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the MaterialsCodeGraph MCP server delete data?

Yes. 3 tools can delete, cancel or revoke something: mcg_delete_study, mcg_archive and mcg_cancel_run.

Can the MaterialsCodeGraph MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the MaterialsCodeGraph MCP server have?

15 tools: 3 destructive, 7 write, 5 read. mcg_delete_study, mcg_archive, mcg_cancel_run, mcg_catalog, mcg_rates, mcg_quote, mcg_clusters, mcg_stage and 7 more.

Does the MaterialsCodeGraph MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the MaterialsCodeGraph MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the MaterialsCodeGraph MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.