Purpose and audience

This spec is for AI and agent teams connecting LLMs and autonomous agents to the live web through Nimble's hosted Model Context Protocol (MCP) server. Any MCP-compatible host, including Claude, ChatGPT, Cursor, and agent frameworks such as LangChain, can call Nimble's web search and retrieval tools directly and get back cited, structured results.

For installation, authorization, and a live verification call, start with Nimble Agent Setup.

What the MCP server gives an agent

Nimble is web search and retrieval for AI agents. Through MCP, an agent can:

Search the live web and get ranked results with page content
Extract clean content or typed fields from a known URL
Run Extraction Templates for normalized data from popular sources
Map and Crawl a site to discover and retrieve whole sections
Delegate research to Web Search Agents and get back a cited answer or a schema-matched dataset

Tool reference

Tool	What it does	Use when
`nimble_search`	Real-time web search; set `include_answer` for a synthesized, cited answer	The agent needs current web context or a single closed fact
`nimble_extract` / `nimble_extract_async`	Clean markdown, HTML, or parsed fields from a URL, with rendering and browser actions	The agent knows the page and needs its content
`nimble_extract_templates_list` → `_get` → `_run` / `_run_async`	Discover and run maintained Extraction Templates (Amazon, Walmart, Target, Google Search, Google Maps, AI Overviews, ChatGPT, and more)	A named site and a direct item, such as a URL, product ID, or query
`nimble_map`	Discover URLs on a domain	Planning retrieval across a site
`nimble_crawl_run` / `_status` / `_list` / `_terminate`	Retrieve a whole site section	Indexing a docs site or catalog section
`nimble_agents_list` / `nimble_agent_templates_list`	Find an existing Web Search Agent or a gallery template	Before creating a new agent
`nimble_agents_create` / `_update`	Configure a Web Search Agent: skill, goals, sources, effort, output schema, use case	Repeat research, enrichment, or dataset-building work
`nimble_agents_run` → `_run_status` → `_run_result`	Run an agent and collect its cited, schema-matched result	Multi-step research the agent should delegate
`nimble_task_results`	Fetch results of async tasks	After async extract or template runs

Routing guidance

Agents get the best results when they pick the right tool for the task:

Single closed lookup: who or what at a glance, a filing or page pointer → nimble_search (with include_answer for a direct answer).
Named site plus a direct item: an Amazon ASIN, a Google Maps query, a specific URL → check Extraction Templates first, then nimble_extract.
Research, enrichment, or dataset building: "find every…", "enrich this list…", "brief me on…" → a Web Search Agent. Choose the mode (research, enrichment, or dataset building) and set effort from the task: low or medium for quick asks, high as the default when several fields need digging, and x-high or max for complex multi-faceted profiles.
Whole site section: nimble_map, then nimble_crawl_run.

Reference loop: Search → Retrieve → Reason → Verify

Stage	Nimble component	Output
Search	`nimble_search`, focus modes, domain filters	Ranked results with page content
Retrieve	Extract, Extraction Templates, Crawl	Clean markdown or typed fields
Reason	Your LLM, or a Web Search Agent	An answer or dataset
Verify	Citations, verbatim excerpts, graded confidence	Inspectable, auditable output

Web Search Agents run this whole loop for you, and they learn which sources and retrieval paths work. Recurring tasks get faster, more accurate, and up to 50% cheaper over time.

Vector and RAG pipeline fit

Collection: use Search, Extract, or Crawl for documents, and Web Search Agents for structured datasets. Chunk with deterministic IDs (URL + hash + segment).
Indexing: push to your vector store and a relational mirror (Delta or Snowflake) for governance queries. Store the source URL, capture time, locale, and confidence.
Refresh: set TTLs by source type, for example 15 minutes for competitive prices, 1–4 hours for reviews, and daily for documentation. Re-embed only changed chunks.
Delivery: results return through the API, or land in Databricks, Snowflake, or S3/GCS.

Guardrails to reduce hallucinations

Citations first: require a source URL and capture time for every retrieved fact; enforce "no source, no claim" in prompts. Web Search Agents return per-claim citations with verbatim excerpts.
Confidence thresholds: use graded confidence to filter or escalate low-confidence datapoints to human review.
Schema enforcement: define strict output schemas and reject records that fail validation.
Source controls: restrict or prefer domains with include and exclude filters and Search Plans.
Corroboration: for high-stakes facts, require agreement across two or more sources.

Domain examples

AI developer platforms: Qodo replaced a static search index with Web Search Agents to validate code against current libraries and docs. The result was fewer support tickets and higher satisfaction. Case study
GTM and revenue tech: Alta runs millions of pages a day with >99% job success and 3–4× deeper context for its agents. Case study
Retail and CPG: pricing, digital shelf, and reviews research with Extraction Templates and Web Search Agents. See Retail & CPG.
Finance: company and sector research with citations. See Alternative Data for Funds.

Benchmarks

1 overall on the DRACO deep-research benchmark (Nimble x-high: 74.0% overall, 71.6% factual accuracy)
Self-learning: +4.4 points from run 1 to run 3 across four repeat-use domains
Extraction: 90% completeness and 99.1% fetch success across 5,856 URLs

See Nimble Benchmarks.

Security, privacy, and compliance

Customers are controllers; Nimble acts primarily as a processor with DPAs, SOC 2 Type II, and zero-trust controls. Zero Data Retention is available on enterprise plans. Nimble collects public web data only. Trust Center

Pilot checklist (about 90 minutes)

Connect your agent host to Nimble's MCP server (Agent Setup).
Verify nimble_search and nimble_extract with a test query.
Define the facts your agent needs and an output schema.
For repeat research, create a Web Search Agent with that schema and run it at low effort for a preview.
Add guardrails: citations required, a confidence threshold, and source controls.
Index results to your vector store with source metadata and TTLs.
Track KPIs: answer accuracy, citation coverage, freshness, cost per task.
Run a canary of 100 queries, compare to your baseline, then scale.

FAQ

How does MCP reduce hallucinations? It grounds answers in fresh, cited web context with confidence signals and enforced schemas.
Search or Web Search Agent? Use Search when your agent does its own reasoning and needs results fast. Use a Web Search Agent when the task needs multi-step research, citations, and a schema.
Can I deliver to Databricks or Snowflake? Yes, through the API or direct delivery to your warehouse or object storage.

Nimble for AI Agents: MCP Server Technical Spec