Skip to main content
Glama
GaijinEntertainment

Pararam Nexus MCP

search_messages

Search for messages across chats using advanced filters, boolean operators, and wildcards to locate specific conversations or content.

Instructions

Search for messages across all chats or in specific chats.

Args: query: Search query string. Supports search filters (see below) limit: Maximum number of results to return (default: 20) chat_ids: Optional list of chat IDs to search within. If None, search in all chats.

Search Syntax: Boolean Operators: By default, all terms are optional (OR), as long as one term matches. Search for "foo bar baz" finds any document containing foo OR bar OR baz.

    + (must be present) - Example: +fox (fox must be found)
    - (must not be present) - Example: -news (news must be excluded)
    Example: "quick brown +fox -news" (fox required, news excluded, quick/brown optional)

    AND, OR, NOT (also &&, ||, !) - Standard boolean operators
    NOTE: NOT takes precedence over AND, which takes precedence over OR
    Example: "(quick OR brown) AND fox"

Grouping:
    Use parentheses to group terms: "(quick OR brown) AND fox"

Wildcards:
    ? - Replace single character: "qu?ck"
    * - Replace zero or more characters: "bro*"

Strict Search:
    Use quotes for exact phrase match: "some search phrase"

Fuzziness:
    Use ~ for similar terms (Damerau-Levenshtein distance, max 2 changes):
    "quikc~ brwn~ foks~" or "quikc~1" (edit distance of 1)

Proximity Search:
    Use ~N after phrase to allow words to be N positions apart:
    "fox quick"~5 (allows up to 5 words distance, any order)

Search Filters: Format: search text /filter1 param1 param2 /filter2 param

/users or /from - Find posts by specific users
    Example: /users @user1 @user2 or /from @user1 @user2

/replyto or /reply - Find messages that are replies to specified users
    Example: /replyto @user1 @user2 or /reply @user1 @user2

/to - Find messages that mention users OR are replies to them
    Example: /to @user1 @user2

/file - Find files by name pattern
    Example: /file *filen?me*

/from_date or /after - Find posts created after a date (YYYY-MM-DD, YYYY-MM, or YYYY)
    Example: /from_date 2016-01-22 or /after 2016-01 or /after 2016

/to_date or /before - Find posts created before a date (YYYY-MM-DD, YYYY-MM, or YYYY)
    Example: /to_date 2016-01-22 or /before 2016-01 or /before 2016

/tags - Find posts containing specific tags (strict match)
    Example: /tags hey may day or /tags #hey #may #day or #hey #may #day

/has - Find posts based on content type:
    /has tag - Posts containing tags (e.g., #may)
    /has link - Posts containing URLs or markdown links
    /has email - Posts containing email addresses
    /has mention - Posts mentioning any user or user with role
    /has user - Posts containing user mentions or words starting with @
    /has group - Posts containing role mentions
    /has reply - Posts that are replies
    /has file - Posts with attached files
    /has block - Posts with text in blocks (>text or ```text)
    /has poll - Posts containing polls

Returns: ToolResponse with SearchMessagesPayload containing search results with message text, sender, chat info, and timestamp

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes
limitNo
chat_idsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNoError message if operation failed
messageYesHuman-readable summary of the result
payloadNoThe actual response data
successYesWhether the operation was successful
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does well by detailing search syntax, filters, and return format, which helps the agent understand how the tool behaves beyond basic parameters. However, it doesn't mention performance aspects like rate limits, pagination, or authentication needs, leaving some gaps.

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

Conciseness3/5

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

The description is appropriately front-loaded with the core purpose, but it's lengthy due to detailed search syntax and filters. While this information is valuable, it could be more concise by summarizing or referencing external documentation. Some sections (e.g., boolean operators) are verbose but necessary for clarity.

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 (search with rich syntax), no annotations, and an output schema (implied by 'Returns'), the description is mostly complete. It covers parameters thoroughly and hints at return values, but lacks details on error handling, performance limits, or integration with sibling tools, leaving minor gaps.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate fully. It provides detailed semantics for all three parameters: 'query' with extensive search syntax and filters, 'limit' with its default and purpose, and 'chat_ids' with its optional nature and effect. This adds significant value beyond the bare schema.

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?

The description clearly states the tool searches for messages across all chats or specific chats, providing a specific verb ('search') and resource ('messages'). However, it doesn't explicitly differentiate from sibling tools like 'get_chat_messages' or 'search_chats', which likely have different scopes or purposes.

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?

The description implies usage through its parameter descriptions (e.g., chat_ids for specific chats vs. all chats) but doesn't explicitly state when to use this tool versus alternatives like 'get_chat_messages' (which might retrieve messages without search) or 'search_chats' (which might search chat metadata). No explicit when-not-to-use guidance is provided.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/GaijinEntertainment/pararam-nexus-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server