dexe-mcp

Full DAO report — one call, every section, with a since-diff

dexe_dao_report

Read-onlyIdempotent

Produces a read-only DAO snapshot covering governance, treasury, membership, proposals, and deadlines in one call, with optional unvoted proposals, claimable rewards, and since-based diffs.

Instructions

Read-only. The whole picture of one DAO in one call — every section named by sections (default all), plus everything with a DEADLINE: open votes, executable proposals and, with user, unvoted proposals and claimable rewards. Pass since (ISO timestamp, Unix seconds, block:<n>, or last) for ONLY what changed; each run stores a snapshot so the next since diff has a baseline. Sections degrade independently; unavailable ones are NAMED in unavailable[] with the reason.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "govPool": "<govPool>"
    },
    "name": "dexe_dao_report"
  }
}

Input Schema

Name	Required	Description
`user`	No	Optional wallet. Adds per-user deadline items: proposals in Voting this user has NOT voted on, and claimable rewards.
`since`	No	Diff anchor: ISO-8601 ('2026-08-01T00:00:00Z'), Unix seconds ('1785000000' / 'unix:…'), a block number ('block:62000000'; a bare integer below 1e9 is read as a block), or 'last' to diff against this DAO's previous report run. Omit for a full point-in-time report.
`chainId`	No	Chain to read from: 56 mainnet, 97 testnet. Needs an RPC for it. Default: the configured chain.
`govPool`	Yes	GovPool / DAO address
`persist`	No	Store this run's snapshot so a later `since` diff has a baseline. Full runs only — a `sections`-narrowed run never overwrites it.
`sections`	No	Narrow the report. Default: all of identity, settings, treasury, membership, delegation, experts, validators, proposals, turnout, activity, deadlines.
`memberLimit`	No	Member/delegation rows to fetch (newest joiners first).
`proposalLimit`	No	How many of the NEWEST proposals to walk for state, outcomes and turnout.

Output Schema

Name	Required	Description	Default
`since`	Yes
`chainId`	Yes
`changes`	Yes
`govPool`	Yes
`sources`	Yes
`degraded`	No
`sections`	Yes
`followUps`	Yes
`blockNumber`	Yes
`generatedAt`	Yes
`unavailable`	Yes
`generatedAtUnix`	Yes
`snapshotPersisted`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.37.1Nov 11, 2026

TDQS

A4/5.0

Behavior5/5

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

Adds substantial behavior beyond the annotations: each run stores a snapshot as a diff baseline, sections degrade independently and failures are NAMED in `unavailable[]` with a reason, and per-user deadline items only appear when `user` is supplied. This snapshot-persistence side effect (backed by `persist` defaulting to true) is real operational context the annotations do not convey.

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?

Front-loaded with 'Read-only' and the one-call scope, then parameter-relevant details, so an agent gets the essentials in the first clause. Dense but mostly earning its space; the capitalized emphasis (DEADLINE, ONLY, NAMED) is a minor stylistic cost rather than filler.

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?

For an 8-parameter aggregate read that also emits an output schema, the description covers intent, diff workflow, snapshot persistence, and partial-failure semantics. Return shape is left to the output schema, which is appropriate, and nothing an agent needs to invoke it correctly appears missing.

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 100%, so the baseline is 3; the description largely restates the schema's own parameter docs (default all sections, `since` diff semantics, `user` adding deadline items). It adds the useful nuance that a `sections`-narrowed run never overwrites the snapshot baseline, but nothing about `memberLimit`/`proposalLimit` semantics.

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

Purpose4/5

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

States a specific verb+resource+scope: 'the whole picture of one DAO in one call', enumerating that it returns every section in `sections` plus all deadline-bearing items. An agent can tell this is the aggregate read rather than a narrow one, but no sibling (e.g. dexe_dao_info, dexe_read_dao_stats) is named as the narrower alternative, so differentiation is inferred from wording rather than stated.

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

Usage Guidelines3/5

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

Gives use-mode guidance: omit `since` for a full point-in-time report, pass `since` for 'ONLY what changed', and use `sections` to narrow. However, all of this describes how to configure this one tool; there is no explicit when-to-prefer-this-over-siblings statement or exclusion, leaving the choice against dexe_dao_info / dexe_read_dao_stats to inference.

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

Deploy Server