// SCAN REPORT

Chains API

20 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated: 29 Jun 2026

0 can modify or destroy data

20 read-only

20 tools total

Community server · catalogue entry verified 29/06/2026

How to control Chains API ↓

TOOL MAP

What Chains API exposes to your agents

Read (20) Write / Execute (0) Destructive / Financial (0)

Running more than one server? Check your whole stack →

THE RISK

What can go wrong

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

POLICY

How to control Chains API

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

Cap read operations

{
  "get_chain_by_id": {
    "limits": [
      {
        "counter": "get_chain_by_id_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 Chains API — 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 CHAINS API →

Instant setup, no code required.

FULL CATALOGUE

All 20 Chains API tools

READ 20 tools

Read get_chain_by_id Get detailed information about a specific blockchain chain by its chain ID Read get_chains Get all blockchain chains, optionally filtered by tag (Testnet, L2, or Beacon) Read get_clients Get execution client software (name, version, GitHub repo, language) running on a chain, aggregated from live Read get_endpoints Get RPC, firehose, and substreams endpoints for a specific chain or all chains Read get_keywords Get extracted keywords such as blockchain names, network names, software client names, tags, and relation kind Read get_l2beat_by_id Get L2BEAT scaling data for a single chain by chain ID. Includes stage classification, category, stack, DA lay Read get_refresher_status Get the unified rolling chain refresher\ Read get_relations Get chain relationships (testnet/mainnet, L2/L1, etc.) for a specific chain or all chains Read get_rpc_monitor Get RPC monitor status and summary endpoint health counts across all chains (without per-chain endpoint listin Read get_rpc_monitor_by_id Get RPC endpoint monitoring results for a specific chain by its chain ID Read get_scaling_chains List chains classified by L2BEAT as scaling solutions (Optimistic Rollup, ZK Rollup, Validium, Optimium). Retu Read get_slip44 Get SLIP-0044 coin type information by coin type ID or all coin types Read get_sources Get the status of all data sources (theGraph, chainlist, chains, slip44) Read get_stats Get aggregate statistics: total chains, mainnets, testnets, L2s, beacons, and RPC health percentage Read get_status_page_by_chain Get the operator status/incident page covering a specific chain by its chain ID (e.g. 8453 for Base → base-l2. Read get_status_page_by_symbol Get the operator status/incident page for a coin/network keyed by symbol rather than chain ID (e.g. SOL for So Read get_status_pages Get the curated registry of operator status/incident pages. Returns chain-keyed projects (each with the chainI Read search_chains Search for blockchain chains by name or other attributes Read traverse_relations BFS graph traversal of chain relations from a starting chain. Returns all reachable chains (nodes) and their r Read validate_chains Validate chain data for potential quality issues across 6 validation rules (relation conflicts, slip44 mismatc

FAQ

Questions about Chains API

Is the Chains API MCP server safe to use without restrictions? +

The Chains API server is primarily read-only with 20 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Chains API MCP server expose? +

20 tools across 1 categories: Read. 20 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on Chains API? +

Register the Chains API 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 Chains API tool call.

Deterministic rules across all 20 Chains API tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CHAINS API →

Instant setup, no code required.

20 Chains API tools catalogued and risk-classified — across an index of 43,000+ MCP servers.