bocha-search-mcp

bocha-search-mcp is an MCP server that exposes search tools for AI applications. It provides a general web search tool and an AI-enhanced search tool that returns additional structured “modal cards” (e.g., weather/百科/医疗/列车等) alongside web results.

Evaluated Mar 30, 2026 (22d ago)

Repo ↗ Search mcp search web information-retrieval ai-agents

⚙ Agent Friendliness

/ 100

Can an agent use this?

🔒 Security

/ 100

Is it safe for agents?

⚡ Reliability

/ 100

Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality

Documentation

Error Messages

Auth Simplicity

Rate Limits

🔒 Security

TLS Enforcement

Auth Strength

Scope Granularity

Dep. Hygiene

Secret Handling

Auth is via API key in an environment variable, which is a reasonable practice. However, the README does not describe TLS requirements, scope granularity, rotation practices, or how errors/logging handle sensitive data. Dependency hygiene and CVE status cannot be confirmed from the provided content.

⚡ Reliability

Uptime/SLA

Version Stability

Breaking Changes

Error Recovery

Best When

You are building an MCP-enabled AI agent/workbench (e.g., Claude Desktop) that can call MCP tools and you need web + structured vertical information.

Avoid When

You need a clearly specified public REST API, formal pagination/cursor controls, or detailed reliability/error contract documentation.

Use Cases

• Enable AI agents to perform up-to-date web searches and cite relevant links
• Answer vertical/domain questions using structured outputs (weather, medical, finance, travel, etc.)
• Augment RAG or agent workflows with fresh web context

Not For

• A replacement for authoritative first-party data sources where legal/medical accuracy requirements are strict without human review
• High-assurance retrieval systems requiring explicit SLA/SLO and documented error semantics
• Use cases needing a standard REST/GraphQL/SDK integration path (this is primarily MCP)

Interface

REST API

GraphQL

gRPC

MCP Server

Yes

SDK

Webhooks

Authentication

Methods: API Key (BOCHA_API_KEY)

OAuth: No Scopes: No

README indicates authentication via an API key environment variable. No scope model or fine-grained permissioning details are provided.

Pricing

Free tier: No

Requires CC: No

Pricing not stated in the provided README content; a link to an open platform exists for obtaining an API key.

Agent Metadata

Pagination

count-based (count 1-50) with freshness filter; no cursor described

Idempotent

False

Retry Guidance

Not documented

Known Gotchas

⚠ Pagination/cursor behavior is not documented beyond a count limit (1-50).
⚠ No documented retry/backoff semantics for transient failures.
⚠ Tool outputs include freshness and count parameters but structured schema details (field names/types) are not fully specified in the provided README excerpt.

Alternatives

Bing Search API / Microsoft search endpoints (noting snippet/region/region-specific considerations) Other MCP web-search servers (where OpenAPI-like contracts and error semantics are better documented) Direct web search + your own vertical extraction pipelines

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for bocha-search-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

API endpoint ↗ Agent guide ↗ Report inaccuracy

Scores are editorial opinions as of 2026-03-30.