Merkl MCP Server

Aggregate Max

opportunities-aggregate-max

Compute the maximum value of a chosen numeric field, such as APR or TVL, across Merkl opportunities filtered by chain, protocol, or status.

Instructions

GET /v4/opportunities/aggregate/max/{field}

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No	Filter by name
`tags`	No	Filter by tag
`test`	No	Include opportunities with test campaigns
`type`	No	A comma separated list of Opportunity type
`field`	Yes	Numeric field to compute max on (e.g. apr, tvl, dailyRewards)
`point`	No	Include opportunities with point campaigns
`action`	No	A comma separated list actions. Legal values: POOL,HOLD,DROP,LEND,BORROW,LONG,SHORT,SWAP,INVALID
`search`	No	Search amongst multiple values (token, protocols, tags, campaigns)
`status`	No	A comma separated list of status. Legal values: LIVE,PAST,SOON
`tokens`	No	A comma separated list of token symbol. Use to filter by token
`chainId`	No	A comma separated list of chain ids. Example: ?chainId=1,42161
`campaigns`	No	Include campaign data. Will slow down the request
`chainName`	No	A comma separated list of chain names. Example: ?chainName=ethereum,arbitrum
`campaignId`	No	Search the opportunity linked to a given campaignId
`identifier`	No	Filter by identifier (mainParameter)
`maximumApr`	No	Maximum APR threshold
`maximumTvl`	No	Maximum TVL threshold in USD
`minimumApr`	No	Minimum APR threshold
`minimumTvl`	No	Minimum TVL threshold in USD
`tokenTypes`	No	Filter by token type. Use POINT to include point campaigns and PRETGE to include preTGE campaigns.
`creatorSlug`	No
`programSlugs`	No	A comma separated list of program ids or slugs. See GET /v4/programs
`creatorAddress`	No	Filter by creator address
`mainProtocolId`	No	A comma separated list of protocol ids. See GET /v4/protocols
`distributionTypes`	No	Filter by distribution type. Legal values: FIX_REWARD, MAX_REWARD, DUTCH_AUCTION
`rewardTokenSymbol`	No	Filter by opportunity with at least 1 campaign where the reward token has this symbol
`excludeSubCampaigns`	No	Exclude sub-campaigns from the results

Output Schema

TableJSON Schema

Name	Required	Description	Default
`value`	Yes	Maximum value for the requested field across matching opportunities

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.9Sep 13, 2026

TDQS

D1.7/5.0

Behavior1/5

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

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing: no authentication requirements, no rate limits, no note on whether filters apply before aggregation, and no indication that the path parameter is required. A bare URL template is insufficient for a read tool with 27 parameters.

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

Conciseness2/5

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

The description is a single short line with no padding, but its brevity comes from under-specification rather than efficient communication. Nothing is front-loaded because there is essentially no explanatory content to structure.

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

Completeness1/5

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, but for a 27-parameter aggregation endpoint the description provides no information about aggregation semantics, required inputs, or how the extensive filter set interacts with the max computation. It is completely inadequate for this complexity level.

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 description coverage is 96%, so the schema already documents nearly every parameter thoroughly (including the 'field' parameter with examples like apr, tvl, dailyRewards). The description adds no parameter meaning beyond the schema, so the baseline of 3 applies.

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

Purpose2/5

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

The description is only a raw REST path, 'GET /v4/opportunities/aggregate/max/{field}', which essentially restates the tool name and title rather than explaining in prose what the tool does. It never states that it returns the maximum value of a numeric field across filtered opportunities, nor does it distinguish this from the sibling opportunities-aggregate-min.

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

Usage Guidelines1/5

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

There is no guidance whatsoever on when to use this aggregate instead of opportunities-aggregate, opportunities-aggregate-min, or opportunities-search. No conditions, prerequisites, or alternatives are mentioned.

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

Deploy Server