Skip to main content
Glama

Greynoise

by io.github.pipeworx-io

Search Within a Source

search_within
Read-onlyIdempotent

Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natural-language query; get back the top-N passages with character offsets and similarity scores. Use when the record is too big to cram into the prompt — search_within saves context, returns only the passages that matter, and every passage carries an offset so the agent can verify a verbatim quote. Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document. BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYesThe document text to search inside (max ~200K chars).
limitNoMax passages to return (1-20, default 5).
queryYesNatural-language query — what passages do you want? E.g. "supply-chain risk", "fiscal year 2024 revenue", "drug interactions with warfarin".

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations indicate read-only, idempotent, and non-destructive behavior. The description adds technical details: BGE-base-en embeddings, cosine similarity, 500-char overlapping windows, 200K char limit with truncation flag, and that results include character offsets and similarity scores. This is valuable beyond annotations, though a perfect score would require more on idempotency guarantee.

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?

The description is moderately long but each sentence is purposeful: purpose, use case, technical details, pairing. It is front-loaded with the primary action. Minor redundancy (e.g., 'P pairs with' could be more concise), but overall efficient.

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?

No output schema, but the description explains returns: top-N passages with character offsets and similarity scores. Covers input limits, embedding details, window size, truncation behavior, and pairing with another tool. Fully addresses what an agent needs to know to use and interpret results.

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?

All three parameters have schema descriptions (100% coverage). The description enriches with examples for query ('supply-chain risk', etc.), default behavior for limit (1-20, default 5), and context for text (max ~200K chars). This goes beyond the schema but doesn't add critical missing info.

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 clearly states 'Semantic search INSIDE a fetched record', using a specific verb (search) and resource (record). It distinguishes from siblings by specifying it works inside a fetched document, contrasting with 'ask_pipeworx_grounded' which is mentioned as a paired tool for grounding over passages.

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

Usage Guidelines5/5

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

Explicitly advises using when the record is too big for the prompt, emphasizing context savings. Mentions pairing with 'ask_pipeworx_grounded' for grounded reasoning, providing clear when-to-use and alternatives.

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

All Greynoise toolsInspect
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

A3.7/5.0
Disambiguation2/5

ask_pipeworx and ask_pipeworx_beta are explicitly identical right now, creating a true duplicate entry point, and the prediction-market cluster (bet_research, polymarket_arbitrage, polymarket_edges, polymarket_kalshi_spread) all detect mispricings with heavily overlapping descriptions. The detailed docs help, but an agent choosing among these will frequently misselect.

Naming Consistency3/5

The set mixes verb-first names (ask_pipeworx, compare_entities, discover_tools, subscribe) with noun-first names (polymarket_edges, entity_profile, ip_context, recent_changes) and bare verbs (remember, forget) without a unifying convention. Subfamilies are internally consistent (polymarket_*, ask_pipeworx_*, subscribe/unsubscribe), which keeps it readable, but there is no predictable server-wide pattern.

Tool Count2/5

32 tools is well into the too-many band, and several tools duplicate or wrap others: ask_pipeworx_beta is a redundant copy of ask_pipeworx, scan_competitor_ai_presence wraps ai_visibility_check, and bet_research overlaps polymarket_edges/arbitrage. The broad scope justifies a large set, but it would be tighter and clearer around 20-24 tools.

Completeness4/5

For the domain the descriptions actually define (structured-data research, company intelligence, prediction markets, subscriptions, memory), coverage is strong with few dead ends: subscription and memory lifecycles are complete, and research has routing/grounded/deep modes. However, the server is named Greynoise while only ip_context serves that domain, and side tools like generate_llms_txt and scan_dependency sit outside any core workflow.

Resources