peerlytics

list_activity

Protocol activity feed. Recent protocol events. Pass since (lower bound) and to (upper bound) for an explicit window, or range for a shortcut. The response includes next_cursor whenever has_more=true; pass it back as cursor to walk older events without offset drift.

Input Schema

TableJSON Schema

Name	Required	Description
`to`	No	Window upper bound (exclusive). ISO-8601 or unix-seconds. Defaults to `now` when omitted but `from` is supplied.
`type`	No	Repeatable event types
`limit`	No	Max number of results to return.
`range`	No	Unified date-range shortcut shared across analytics + explorer endpoints. Hard cap: 400-day window. When set, takes precedence over `from`/`to`. Legacy values (`3mtd`, `q1`-`q4`, `custom`) were retired on 2026-04-30; use the explicit shortcuts below.
`since`	No	Lower bound for event timestamps (unix seconds, ms, or ISO). Replaces the legacy `after` alias.
`taker`	No
`cursor`	No	Pass the previous page's `next_cursor` to walk forward without offset drift. This is the supported pagination path on every list endpoint.
`offset`	No	Deprecated. Use `cursor` instead — offset pagination is fragile under concurrent writes and slow at scale. Still accepted for backwards compatibility while integrators migrate.
`address`	No	Filter by any address involved
`depositor`	No
`recipient`	No
`deposit_id`	No
`intent_hash`	No

TDQS

A4/5.0

Behavior4/5

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

Given no annotations, the description effectively discloses pagination behavior (cursor/offset), parameter precedence (range overrides from/to), and retirement of legacy values. It adds significant behavioral context beyond mere existence.

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 two focused sentences: one for purpose, one for parameter usage. It is front-loaded and every sentence adds value. No redundancy or filler.

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?

The description handles 13 parameters by explaining pagination and date range logic, but does not cover all filter parameters (e.g., taker, depositor). The response structure is partially described (next_cursor, has_more). Good, but leaving some parameter details to the schema.

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 62%, but the description adds meaning by explaining the relationship between range, since, to, cursor, and offset. It clarifies the pagination contract and shortcut behavior, surpassing what the schema provides.

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 states 'Protocol activity feed. Recent protocol events.' This clearly identifies the tool as listing activity events, distinguishing it from sibling list tools for currencies, deposits, and intents.

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

Usage Guidelines2/5

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

The description does not provide explicit guidance on when to use this tool versus alternatives. It lacks context on when not to use it or how it differs from related tools like list_deposits or list_intents.

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

All peerlytics tools Inspect

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

C2.8/5.0

Disambiguation3/5

Most get_* and list_* tools target distinct domain entities, but several high-level analytics endpoints overlap in purpose (get_analytics_summary, get_protocol_overview, get_market_summary, get_timeseries, get_leaderboard), and pairs like get_deposit/get_deposit_context and get_vault/get_vault_analytics create close boundaries. The descriptions clarify the differences, but an agent would need to read carefully to avoid misselection.

Naming Consistency5/5

The tool set follows a strong verb_noun pattern: get_ for single-entity or detail views, list_ for collections, plus explicit action endpoints like export_trade_log, plan_routes, and search_explorer. All names are snake_case and predictable, with no mixing of conventions.

Tool Count3/5

28 tools is on the heavy side for an MCP server, even for a broad analytics domain. Most tools map to real entities, but the surface is padded by overlapping summary/analytics endpoints and separate detail, context, and analytics variants for the same resources.

Completeness4/5

The server provides broad read-only coverage of the protocol domain: deposits, intents, makers, takers, vaults, delegates, verifiers, platforms, integrators, orderbook, routes, activity, and search. Minor gaps such as no list_vaults or list_integrators are workable via search/get endpoints, and mutating operations appear out of scope for an analytics-focused server.

Resources

Need Help?