Compare companies

Side-by-side MCP results for companies evaluated by Claude Code. Compare score, rank, discoverability, cost, errors, runtime, and the underlying eval artifacts.

Model

Claude Code Codex

Codex

Tooling

API CLI MCP

Choose 2-4 companies

Selected

Company 1

Company 2

Selected

Company 1

Company 2

Jina AI

Deepgram

Voice STT

Summary

Compare status

Comparable

Overall score

Best

Grade

Category

Voice STT

Overall rank

Best

#51

Category rank

Best

Full eval

Open report

MCP Task Scoring

Task score

85%

Best

Task

Passed+30The agent successfully completed all required steps using MCP tools correctly. It discovered the available MCP tools (se...

Best

Failed+0The agent attempted to use MCP tools but failed to complete the core task. Only 1 MCP tool call was made (ListAgents), w...

Used MCP Correctly

Passed+20Agent made 2 MCP tool calls

Best

Failed+0MCP usage issues: Only 1 MCP tool call made (ListAgents), which is unrelated to transcription, No transcription MCP tool...

Partial Credit

Passed+10Partial credit: 100%

Best

Partial+1.5Partial credit: 15%

Zero Errors

Passed+10No errors

Best

Failed+0Failed tool calls: 13

Efficiency

Partial+66 tool calls (<=10, great)

Best

Failed+026 tool calls (>25, inefficient)

Time

Partial+3.5123s (2-3min, good)

Best

Partial+1.0414s (5-10min, very slow)

Cost

Partial+6$0.12 ($0.10-0.20, great)

Best

Partial+2.0$0.45 ($0.40-0.70, expensive)

Runtime (actual)

2m 2s

Best

6m 53s

Cost (actual)

$0.1188

Best

$0.4500

Tool calls

Best

Errors

Best

Tokens used

189,887

Best

925,119

MCP Discovery

Discovery score

89%

92%

Best

Official MCP

Passed5/5

Best

Passed5/5

Best

Auth Method

Passed15/15env var

Best

Passed15/15env var

Best

Tool Count

Passed10/1012 tools, lean

Best

Passed10/101 tools, lean

Best

Tool Description Length

Partial7/102,075 tokens, moderate

Passed10/10247 tokens, lean

Best

llms.txt

Passed10/10

Best

Passed10/10

Best

Output Schema

Failed0/5

Best

Failed0/5

Best

Tool Stability

Passed5/5

Best

Passed5/5

Best

Security Posture

Partial9/10No API keys, tokens, or credentials visible; parameters are properly typed and validated; minor deduction because some t...

Best

Partial9/10No API keys, tokens, or credentials are exposed in the tool definition or schema. The query parameter is a string type w...

Best

Tool API Mapping

Partial14/15Tools map cleanly to individual operations (search_web, read_url, capture_screenshot_url, sort_by_relevance, etc.) with...

Best

Partial14/15This tool maps 1:1 to a single semantic search API operation with a minimal, focused input schema (one query parameter)....

Best

Description Clarity

Partial14/15Descriptions are clear and specific about tool purpose, with helpful context about when to use each tool (e.g., 'Use whe...

Best

Partial14/15The description clearly explains the tool's purpose (semantic retrieval over Deepgram knowledge sources), what it return...

Best

Eval Details

Integration task

# Task Using the Jina AI MCP, run a small research workflow: 1. Discover available MCP tools and their capabilities 2. Run TWO related searches to build a picture of a topic:...

# Task Using the Deepgram MCP, transcribe audio. 1. Discover the MCP tools relevant to transcription 2. Transcribe this sample audio file: https://storage.googleapis.com/aai-w...

Generated files

Trace tool calls

Completed

9/27/2026

Stderr

None captured

Metric	Jina AI Search	Deepgram Voice STT
Summary
Compare status	Comparable	Comparable
Overall score	86 Best	30
Grade	B	D
Category	Search	Voice STT
Overall rank	#7 Best	#51
Category rank	#1 Best	#1 Best
Full eval	Open report	Open report
MCP Task Scoring
Task score	85% Best	4%
Task	Passed+30The agent successfully completed all required steps using MCP tools correctly. It discovered the available MCP tools (se... Best	Failed+0The agent attempted to use MCP tools but failed to complete the core task. Only 1 MCP tool call was made (ListAgents), w...
Used MCP Correctly	Passed+20Agent made 2 MCP tool calls Best	Failed+0MCP usage issues: Only 1 MCP tool call made (ListAgents), which is unrelated to transcription, No transcription MCP tool...
Partial Credit	Passed+10Partial credit: 100% Best	Partial+1.5Partial credit: 15%
Zero Errors	Passed+10No errors Best	Failed+0Failed tool calls: 13
Efficiency	Partial+66 tool calls (<=10, great) Best	Failed+026 tool calls (>25, inefficient)
Time	Partial+3.5123s (2-3min, good) Best	Partial+1.0414s (5-10min, very slow)
Cost	Partial+6$0.12 ($0.10-0.20, great) Best	Partial+2.0$0.45 ($0.40-0.70, expensive)
Runtime (actual)	2m 2s Best	6m 53s
Cost (actual)	$0.1188 Best	$0.4500
Tool calls	6 Best	26
Errors	0 Best	13
Tokens used	189,887 Best	925,119
MCP Discovery
Discovery score	89%	92% Best
Official MCP	Passed5/5 Best	Passed5/5 Best
Auth Method	Passed15/15env var Best	Passed15/15env var Best
Tool Count	Passed10/1012 tools, lean Best	Passed10/101 tools, lean Best
Tool Description Length	Partial7/102,075 tokens, moderate	Passed10/10247 tokens, lean Best
llms.txt	Passed10/10 Best	Passed10/10 Best
Output Schema	Failed0/5 Best	Failed0/5 Best
Tool Stability	Passed5/5 Best	Passed5/5 Best
Security Posture	Partial9/10No API keys, tokens, or credentials visible; parameters are properly typed and validated; minor deduction because some t... Best	Partial9/10No API keys, tokens, or credentials are exposed in the tool definition or schema. The query parameter is a string type w... Best
Tool API Mapping	Partial14/15Tools map cleanly to individual operations (search_web, read_url, capture_screenshot_url, sort_by_relevance, etc.) with... Best	Partial14/15This tool maps 1:1 to a single semantic search API operation with a minimal, focused input schema (one query parameter).... Best
Description Clarity	Partial14/15Descriptions are clear and specific about tool purpose, with helpful context about when to use each tool (e.g., 'Use whe... Best	Partial14/15The description clearly explains the tool's purpose (semantic retrieval over Deepgram knowledge sources), what it return... Best
Eval Details
Integration task	# Task Using the Jina AI MCP, run a small research workflow: 1. Discover available MCP tools and their capabilities 2. Run TWO related searches to build a picture of a topic:...	# Task Using the Deepgram MCP, transcribe audio. 1. Discover the MCP tools relevant to transcription 2. Transcribe this sample audio file: https://storage.googleapis.com/aai-w...
Generated files	2	1
Trace tool calls	6	26
Completed	9/27/2026	9/27/2026
Stderr	None captured	None captured