// SCAN REPORT

Fairchem

24 tools. 18 can modify or destroy data without limits.

18 write tools that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

18 can modify or destroy data

6 read-only

24 tools total

Community server · catalogue entry verified 02/07/2026

How to control Fairchem ↓

TOOL MAP

What Fairchem exposes to your agents

Read (6) Write / Execute (18) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Fairchem tools

Execute · Critical execute This tool allows execution of arbitrary Python code in a persistent session, which can invoke any available libraries, modify simulation states, access file systems, and trigger external operations. Execute · High start_convex_hull Convex hull calculations in materials science typically involve triggering external simulation operations whose effects depend on input structures and parameters. Execute · High start_elastic_scan An elastic scan is a scientific computation that explores energy surfaces across structural deformations. Execute · High start_eos_scan This tool triggers execution of a complex computational workflow (equation-of-state scanning) that runs external simulation code.

18 of Fairchem's 24 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Fairchem

PolicyLayer is an MCP gateway — it sits between your AI agents and Fairchem, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "attach_emt": {
    "limits": [
      {
        "counter": "attach_emt_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_results": {
    "limits": [
      {
        "counter": "get_results_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Fairchem — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON FAIRCHEM →

Instant setup, no code required.

FULL CATALOGUE

All 24 Fairchem tools

EXECUTE 16 tools

Execute build_structure build_structure Execute execute Execute Python in the persistent session namespace (escape hatch). Execute inspect_expr Evaluate an expression in the session namespace and return its repr. Execute load_model Load a FAIRChem model as an ASE calculator, kept resident in memory. Execute start_convex_hull start_convex_hull Execute start_elastic_scan start_elastic_scan Execute start_eos_scan start_eos_scan Execute start_md Start molecular dynamics (NVT Langevin or NVE) in the background. Execute start_minima_search start_minima_search Execute start_neb start_neb Execute start_phonons start_phonons Execute start_pounce_saddles start_pounce_saddles Execute start_relaxation start_relaxation Execute start_saddle_search start_saddle_search Execute start_sella_search start_sella_search Execute steer steer

WRITE 2 tools

Write attach_emt Attach a fast EMT calculator (no GPU/model needed). Useful for quick tests Write attach_lammps attach_lammps

READ 6 tools

Read get_results Return a job's final results, if any: NEB barrier/energies, phonon gamma Read get_status Get a live snapshot of a job: status, step, energy, max_force, and a Read get_trajectory Return the recent energy/force history of a job (last_n snapshots). Read introspect introspect Read list_models List FAIRChem pretrained models (UMA, eSEN, ...) if FAIRChem is installed. Read load_structure Load a structure from any ASE-readable file (cif, xyz, traj, POSCAR, ...).

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Fairchem

How do I prevent bulk modifications through Fairchem? +

The Fairchem server has 2 write tools including attach_emt, attach_lammps. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Fairchem.

How many tools does the Fairchem MCP server expose? +

24 tools across 3 categories: Execute, Read, Write. 6 are read-only. 18 can modify, create, or delete data.

How do I enforce a policy on Fairchem? +

Register the Fairchem MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Fairchem tool call.

Deterministic rules across all 24 Fairchem tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FAIRCHEM →

Instant setup, no code required.

24 Fairchem tools catalogued and risk-classified — across an index of 43,000+ MCP servers.