Skip to main content
Glama

Seneschal Data

by io.github.Rotwang9000

Counter-MEV / approval-risk intelligence

seneschal_counter_mev

Defensive intel for MEV searchers and bot operators. Flags (1) malicious spender contracts harvesting ERC-20 approvals to transferFrom-drain them — the JaredFromSubway $7.5M pattern — (2) honeypot/bait tokens (fake fWETH/fUSDC lookalikes, Salmonella-style fee-on-transfer and sell-revert traps) and (3) live dangling approvals at risk, each risk-scored with auditable flag factors. view="summary" returns counts + score distribution + a teaser; view="detail" returns the full uncapped feed (paid via x402 at GET /v1/premium/counter-mev; served here for agents); pass address to check one address. Verify on-chain before acting.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
viewNosummary (default) = aggregates + teaser; detail = full risk-scored feed.
limitNodetail view: per-category row cap (1..500). Default 200.
addressNoIf set, return a single-address risk lookup instead of the feed.
categoryNodetail view: restrict to one category. Default all.
min_scoreNodetail view: drop entries below this risk score (0..100). Default 0.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and does well: it discloses that the tool flags specific risk types, returns counts/teaser in summary, full feed in detail, supports address lookup, mentions the premium payment route, and advises 'Verify on-chain before acting.' This gives a clear behavioral picture beyond the schema.

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?

The description is information-dense and well-structured, starting with purpose, then enumerating risk categories, then view semantics. The colorful examples (JaredFromSubway, Salmonella-style) add flavor but are not essential, making it slightly longer than pure functionality would require. Every other sentence serves a purpose.

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?

Given the tool's complexity (5 parameters, no output schema), the description covers the main return values (summary counts/score distribution/teaser, detail feed, address lookup) and mentions the 'uncapped' feed and 'auditable flag factors.' The slight mismatch between 'full uncapped feed' and the schema's limit cap (1..500) creates minor ambiguity, but overall it is fairly complete.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3; the description adds value by explaining the semantic difference between 'summary' and 'detail' views and that passing an 'address' returns a single-address lookup. It does not elaborate on 'limit', 'category', or 'min_score', but schema already describes those adequately.

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 clearly states the tool provides defensive intel for MEV searchers and bot operators, and enumerates three specific risk categories it flags (malicious spenders, honeypot tokens, dangling approvals). It distinguishes itself from sibling tools through its unique MEV/approval-risk focus and explicit verbiage like 'Flags' and 'risk-scored with auditable flag factors.'

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 gives clear context on target users (MEV searchers and bot operators) and explains the different views (summary vs detail) and address lookup, but does not explicitly mention when not to use the tool or alternatives. It does note the paid x402 endpoint and advises verifying on-chain, which helps set usage expectations.

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

All Seneschal Data toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation4/5

Tools are grouped by domain (board, private_watch, zecmon) with clear lifecycle separation, but seneschal_list_at_risk_borrowers and seneschal_list_borrowers overlap heavily, and the USDC vs crypto variants of private_watch_create/topup could be confused without careful reading.

Naming Consistency4/5

Most tools follow a seneschal_<domain>_<action> pattern, but verb/noun order varies (get_borrower vs list_borrowers vs board_list) and outliers like seneschal_health and seneschal_q break the pattern.

Tool Count3/5

At 35 tools, the server is definitely heavy, but it covers multiple distinct domains (DeFi data, privacy-chain monitoring, notice boards, payments), so the count is at the high end of reasonable rather than absurdly bloated.

Completeness4/5

Core workflows are well covered: borrower discovery/analysis, liquidations, private watch lifecycle, Zcash scanning lifecycle, board operations, and checkout invoices. Minor gaps like board deletion or watch cancellation exist but are workaround-able.

Resources