Chainladder MCP server

by datalattice·io.github.datalattice/mcp-chainladder·v1.2.2

No reviews yet

Actuarial chain-ladder reserving: IBNR, Mack stochastic stats, and assumption diagnostics.

B78/100grade B

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

B78/100

full report

Adoption

New

0 stars20 downloads/wk

Reviews

Write one

Nobody has reviewed Chainladder yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Chainladder tools (14, 4 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

bornhuetter_ferguson
Bornhuetter-Ferguson (1972) reserving method. **Pro tier.**
compare_methodswrite action
Run chain ladder + Bornhuetter-Ferguson on the same triangle and return a side-by-side comparison. **Pro tier.**
compute_chain_ladderwrite action
Run a full chain-ladder reserving calculation on a cumulative loss triangle. This is the workhorse tool — call it whenever the user asks "what's the IBNR?", "what does the chain ladder say?", or hands you a triangle and asks for projections.
interpret_diagnosticswrite action
Run Mack assumption diagnostics + label each result with a plain- English verdict and a recommended action. **Pro tier.**
mack_diagnostics
Mack (1994) assumption diagnostics — three statistical tests plus standardised-residual outlier detection. Use when the user asks "does the chain ladder look OK?", "are there any outliers?", or "should I be worried about [calendar-year / inflation / dependence] effects?".
mack_stochastic
Mack (1993) stochastic chain-ladder error estimation. Returns distribution-free standard errors and coefficients of variation per accident row plus the totals — the canonical sensitivity check for a deterministic chain-ladder result.
parse_csv_triangle
Parse a CSV file from disk into a cumulative loss triangle.
pro_license_status
Inspect the current Pro-tier license state. Returns whether Pro tools are unlocked, the registered owner, an expiry date if any, and a human-readable message that Claude can relay to the user. Free to call regardless of license state.
project_triangle
Fill the lower-right (unobserved) cells of a cumulative triangle using the supplied age-to-age factors.
sample_triangle
Return the classic textbook 10×10 cumulative-paid triangle (Friedland-style). Useful for demos, examples, and verifying the server is working — feed it to `compute_chain_ladder` to get the well-known parity values (Paid 49,458 / Ultimate 65,883 / IBNR 16,425 / Mack SE ±354.61).
sensitivity_analysiswrite action
Drop each observable link ratio one at a time, rerun the chain ladder, and rank the link ratios by their impact on total IBNR. **Pro tier.**
tail_extrapolation
Fit parametric tail models to the late development factors and extrapolate forward. **Pro tier.**
to_cumulative
Convert an incremental triangle to cumulative (running sum per row). Unobserved cells propagate as null. Inverse of `to_incremental` on observed cells.
to_incremental
Convert a cumulative triangle to incremental (per-period) values.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings

Code scan10 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 136 days ago8/15
Maintainer identityregistry namespace matches repository owner6/10

Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How Chainladder compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 78/100; higher than 57% of 48,255 servers
Tools: 14; the typical server has 7
Tools that change things: 29%; typical: 0%. Fewer write tools means less an agent can break
Downloads a week: 20; more than 7% of 12,191 servers with a package

What its tools let an agent do: 10 read · 4 change

Install Chainladder in Claude Code, Cursor or VS Code

claude mcp add mcp-chainladder -- uvx mcp-chainladder

Add to Cursor

What the publisher says

From the Chainladder repository's README, as published. We do not edit it. Read it on GitHub

mcp-chainladder

Actuarial chain-ladder reserving for Claude. A Model Context Protocol server that hands Claude the tools to compute IBNR, project ultimates, run Mack (1993) stochastic error estimates, check Mack (1994) model assumptions, and parse loss triangles from CSV — all from a natural- language conversation.

Calculation only — not actuarial advice. This is a mechanical

chain-ladder calculator. Selection of data, factors, tails, and

exclusions, and the interpretation of stochastic error measures,

require professional actuarial judgement.

What it does

Eight tools, exposed over MCP. Claude picks the right one when you ask a question; you don't have to call them by name.

All numerical conventions match the Mack 1993 and Mack 1994 papers; results are stable to ~1e-12 against hand calculation on the textbook 10×10 triangle.

Install

pipx install mcp-chainladder
# or, to run on demand without installing:
uvx mcp-chainladder

Python 3.10 or newer; no other runtime dependencies beyond the official MCP SDK.

Hook into Claude Desktop

Edit ~/Library/Application Support/Claude/claudedesktopconfig.json (macOS) or %APPDATA%\Claude\claudedesktopconfig.json (Windows):

{
  "mcpServers": {
    "chainladder": {
      "command": "uvx",
      "args": ["mcp-chainladder"]
    }
  }
}

Quit and reopen Claude Desktop. The triangle tools appear under the 🔌 icon in any conversation.

For Cursor / Cline / Continue / Zed — same mcpServers block, each app has its own config file location (their docs walk you through it).

Examples

Run the chain ladder on a CSV

Me: I have a paid-loss triangle at ~/Desktop/motor_2026Q1.csv.
    Run the chain ladder and tell me the IBNR.

Claude: [calls parse_csv_triangle, then compute_chain_ladder]
        Loaded a 10×10 cumulative triangle. Using volume-weighted
        factors:
          • Total paid to date: 49,458,000 USD
          • Total ultimate:     65,883,400 USD
          • Total IBNR:         16,425,400 USD
        Selected factors trend from 1.879 at the front of the
        triangle down to 1.002 at the tail.

Check whether you should worry about assumptions

Me: Same triangle — any reason not to trust the projection?

Claude: [calls mack_diagnostics]
        Three flags worth a look:
        • Inflation trend: slope 0.053, p ≈ 1e-12 — STRONG evidence
          link ratios are drifting upward across accident years.
          This violates Mack's homogeneity assumption; consider
          weighting recent years more.
        • Calendar-year: Z = 0.0, p = 1.0 — no diagonal effect.
        • Independence: Z = -0.35, p = 0.73 — no obvious dependence
          across development columns.
        • Outliers: 0 cells exceed |2σ|.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Chainladder: common questions

Is Chainladder MCP server safe?: Mostly: it is graded B (78/100). Read the Chainladder safety report
How do I install Chainladder?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Chainladder need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Chainladder maintained?: The last commit was 173 days ago (2026-05-14). The latest release is v1.2.2.
How does Chainladder compare with other MCP servers?: safety score 78/100 (higher than 57% of 48,255 servers); tools 14 (the typical server has 7); tools that change things 29% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.