Skip to main content
Glama
jflamb

FDIC BankFind MCP Server

by jflamb

Peer Group Analysis

fdic_peer_group_analysis
Read-onlyIdempotent

Build a peer group for any FDIC-insured bank and rank it against peers on key financial metrics like ROA, efficiency ratio, and more at a single report date. Supports subject-driven, explicit criteria, or overrides for flexible analysis.

Instructions

Build a peer group for an FDIC-insured institution and rank it against peers on financial and efficiency metrics at a single report date.

Three usage modes:

  • Subject-driven: provide cert and repdte — auto-derives peer criteria from the subject's asset size and charter class

  • Explicit criteria: provide repdte plus asset_min/asset_max, charter_classes, state, or raw_filter

  • Subject with overrides: provide cert plus explicit criteria to override auto-derived defaults

Metrics ranked (fixed order):

  • Total Assets, Total Deposits, ROA, ROE, Net Interest Margin

  • Equity Capital Ratio, Efficiency Ratio, Loan-to-Deposit Ratio

  • Deposits-to-Assets Ratio, Non-Interest Income Share

Rankings use competition rank (1, 2, 2, 4). Rank, denominator, and percentile all use the same comparison set: matched peers plus the subject institution.

Output includes:

  • Subject rankings and percentiles (when cert provided)

  • Peer group medians

  • Peer list with CERTs (pass to fdic_compare_bank_snapshots for trend analysis)

  • Metric definitions with directionality metadata

Override precedence: cert derives defaults, then explicit params override them.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
certNoSubject institution CERT number. When provided, auto-derives peer criteria and ranks this bank against peers.
repdteNoReport Date (REPDTE) in YYYYMMDD format. FDIC data is published quarterly on: March 31, June 30, September 30, and December 31. Example: 20231231 for Q4 2023. If omitted, defaults to the most recent quarter-end date likely to have published data (~90-day lag).
asset_minNoMinimum total assets ($thousands) for peer selection. Defaults to 50% of subject's report-date assets when cert is provided.
asset_maxNoMaximum total assets ($thousands) for peer selection. Defaults to 200% of subject's report-date assets when cert is provided.
charter_classesNoCharter class codes to include (e.g., ["N", "SM"]). Defaults to the subject's charter class when cert is provided.
stateNoTwo-letter state code (e.g., "NC", "TX").
raw_filterNoAdvanced: raw ElasticSearch query string appended to peer selection criteria with AND.
active_onlyNoLimit to institutions where ACTIVE:1 (currently operating, FDIC-insured).
extra_fieldsNoAdditional FDIC field names to include as raw values in the response. Does not affect peer selection.
limitNoMax peer records returned in the response. All matched peers are used for ranking regardless of this limit.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior4/5

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds key behavioral details: ranking uses competition rank (1,2,2,4), all peers are used for ranking regardless of limit, and output includes metric definitions with directionality. No contradiction with annotations.

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

Conciseness5/5

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

The description is well-structured into clear sections (intro, modes, metrics, ranking, output, overrides) with no wasted sentences. It is front-loaded with purpose and each part adds distinct value, earning its place.

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

Completeness5/5

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

Given the tool's complexity (10 parameters, multiple usage modes, and output schema), the description is remarkably complete. It covers ranking method, metric details, output structure, and parameter override logic, leaving no significant gaps.

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

Parameters5/5

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

Schema coverage is 100%, but the description adds substantial meaning: defaults for asset_min/asset_max (50%/200% of subject), charter_classes default to subject's, repdte defaults to most recent quarter, and explains how parameters interact across modes. This goes well beyond the schema's baseline.

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?

The description uses a specific verb 'Build' and resource 'peer group for an FDIC-insured institution', clearly distinguishing the tool's focus on peer construction and ranking. It explicitly lists three usage modes and fixed-ranked metrics, setting it apart from siblings like fdic_compare_bank_snapshots.

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

Usage Guidelines4/5

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

The description details three usage modes (subject-driven, explicit criteria, subject with overrides) and override precedence, guiding the AI on when to use each. It also references fdic_compare_bank_snapshots for trend analysis, indicating an alternative. However, it does not explicitly state scenarios where this tool should be avoided.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jflamb/fdic-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server