Thunderbird MCP

Overview Schema Source Related Servers Discussions Admin

Search everything

search_global

Read-onlyIdempotent

Search indexed Thunderbird mail with ranked results and stable snapshot pagination. Scope queries to a folder, continue with a cursor, and see partial reasons when index limits apply.

Instructions

Ranked search of indexed mail, with stable snapshot pagination.

Start with query, optionally scoped to a folder. Continue with only cursor=nextCursor and limit; a snapshot expires after five minutes or a Thunderbird restart. offset remains for older callers. Coverage is indexed mail only, never a claim that the whole mailbox was searched. partialReasons explains retrieval limits or unavailable index terms. alternativeSearch suggests a literal subject search without running it or silently changing the original query's meaning. Older add-ons retain live offset pages with snapshotSupported=false.

Input Schema

Name	Required	Description	Default
`limit`	No
`query`	No
`cursor`	No
`offset`	No
`folder_id`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv1.4.0Nov 2, 2026

addedInput schema / properties / cursor

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Cursor"
+}

addedInput schema / properties / query / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / query / default
```
Added value: +null
```
removedInput schema / properties / query / type
```
Removed value: -"string"
```
removedInput schema / required
```
Removed value: -[
-  "query"
-]
```

First observedv0.1.0Jul 29, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Annotations already cover safety (readOnly/idempotent/non-destructive), and the description adds genuinely non-obvious behavior: snapshot expiry after five minutes or a Thunderbird restart, indexed-only coverage with an explicit non-claim about the full mailbox, `partialReasons` for retrieval limits, and `snapshotSupported=false` fallback for older add-ons.

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 the one-line definition, then the pagination protocol, then caveats — a sensible ordering with little redundancy. The mid-sentence line wraps make it denser than necessary, and the return-field notes (`partialReasons`, `alternativeSearch`) sit slightly off-topic for a call-time description.

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?

An output schema exists, so explaining return values isn't required, yet the notes on `partialReasons`/`alternativeSearch` add behavioral context rather than restating fields. For a 5-parameter paginated search the description is nearly complete; only limit bounds and ranking/sort behavior remain unstated.

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 description coverage is 0%, so the description must carry the load and largely does: it explains `query` (with optional folder scoping), the cursor+limit continuation contract, `offset` as a legacy path, and folder scoping. `limit` itself is never defined (result count cap, maximum) and folder_id is only alluded to as 'scoped to a folder'.

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?

Opens with a concrete verb+resource+scope: 'Ranked search of indexed mail, with stable snapshot pagination.' The 'indexed mail only, never a claim that the whole mailbox was searched' caveat plus the `alternativeSearch` literal-search mention implicitly separates it from mail_search/search_conversation, but no sibling is named outright.

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?

Gives an explicit call protocol: start with `query` (optionally folder-scoped), then continue with only `cursor=nextCursor` and `limit`; `offset` is explicitly relegated to legacy callers. It does not state when to prefer this over mail_search or search_conversation, so the alternatives dimension is only implied.

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

Deploy Server