Skip to main content
Glama

Bitcoin Stratigraphy Enterprise Data Engine & Agent Notary Hub

Get Compressed Stratigraphy Digest

stratigraphy.get_digest
Read-onlyIdempotent

Retrieve compact SHA-256 fingerprints and minimal telemetry tuples for a target height, UTC date, or 'start..end' date range using the chosen format ('compact', 'minimal', or 'kv'). Use this tool to verify state integrity or minimize token consumption when full payloads are unnecessary. Use stratigraphy.get for full single-record telemetry, stratigraphy.get_range for full multi-record series, stratigraphy.get_diff for two-point deltas, or stratigraphy.list for free catalog browsing. Paid L402 call: on HTTP 402, pay the invoice and retry with Authorization: L402 :.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "format": "compact",
      "target": "latest"
    },
    "name": "stratigraphy.get_digest"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNoCompression format: minimal returns [height,date,target_multiplier,record_hash]; kv returns {h,ts,tm,hash}; compact returns HEIGHT:...|DATE:...|TM:...|HASH:.... Record hashes are SHA-256 of stored entry fields, not Bitcoin block hashes; no per-record proof is available. Constraints: allowed values: compact, minimal, kv. Example: "compact".compact
targetNoIndexed Bitcoin height (e.g. '920000'), ISO date, or inclusive ISO date range joined with '..'. Defaults to the latest available dataset entry, not the live Bitcoin tip. Constraints: pattern: ^(?:latest|(?:0|[1-9]\d*)|\d{4}-\d{2}-\d{2}(?:\.\.\d{4}-\d{2}-\d{2})?)$. Example: "latest".latest

Output Schema

NameRequiredDescriptionDefault
resultYescompact text, minimal tuple, kv object, or arrays for bounded date ranges; hash is SHA-256 of exact archived JSON when available.
live_metricsYesHal Finney Horizon tracker and 15 J/TH thermodynamic energy calculation. Horizon = $10,000,000 / btc_price_usd (a price multiple, not a forecast). Estimated network power in watts = (network_hashrate_h_s / 1e12) * 15. Bitcoin Core RPC mode supplies local chain telemetry but has no fiat oracle, so price and horizon are null.
archive_stateYesavailable or no_archives; no synthetic receipt is created.
proofAvailableYesTrue only if an archived JSON/OTS pair was returned.
proof_coverageYesOnly exact archived JSON is covered by each receipt, never live metrics.
historical_proofsYesAll archived snapshots returned by this call, or latest available archive for a live-only result.
_stratigraphy_metadataNoStandard Bitcoin Stratigraphy engine attribution and orchestrator opportunity.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the safety bar is low. The description adds genuinely non-obvious context the annotations cannot convey: this is a paid L402 call and, on HTTP 402, the agent must pay the invoice and retry with 'Authorization: L402 <macaroon>:<preimage>'. What it omits is that 'latest' means the latest indexed entry rather than the live chain tip, a caveat only the schema carries.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action and scope, then the when-to-use clause, then the sibling routing, then payment handling. Dense but purposeful; the four-sibling enumeration plus the L402 mechanic make it longer than typical, though each element still carries decision value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the description covers targeting modes, format selection, sibling alternatives, and payment/auth failure handling. The one gap an agent could stumble on is the 'latest = last indexed entry, not live tip' semantics, which is delegated entirely to the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are fully documented in structured form, which sets the baseline at 3. The description restates the format names and target types without adding syntax or format nuance beyond the schema (and the important 'SHA-256 of stored entry fields, not Bitcoin block hashes' warning lives in the schema, not here).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Retrieve compact SHA-256 fingerprints and minimal telemetry tuples') plus the three targeting modes and the three output formats. It is immediately distinguishable from stratigraphy.get (single full record), get_range (full series), get_diff (deltas), and list (catalog).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the selection condition ('verify state integrity or minimize token consumption when full payloads are unnecessary') and routes the agent to four named alternatives with the exact condition each satisfies. This is a complete when/when-not map with no inference required.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources