Open Source MCP Server

Your AI assistant's intelligent sidekick

Field Agent uses a lightweight secondary AI model to handle data-heavy tasks — file summaries, log triage, search filtering, and prompt optimisation. Run it locally via Ollama or let our cloud handle it. Two layers of savings that work with any MCP client.

GitHubOpen Source|Works with Claude Code, Cursor, Windsurf, VS Code, Gemini CLI|Patents Pending

Real results, not theory

These are actual recordings from real coding sessions — not simulations, not mockups. Same developer, same task, same AI model. The only difference is whether Field Agent is running. Every token count shown was measured.

Live benchmark data — not theoretical estimates
Without Field Agent
0
0
0
With Field Agent
0
0
0

Where developers waste the most tokens

These are the everyday scenarios that silently burn through your context window and your budget. Field Agent targets each one.

Exploring an unfamiliar codebase

You ask the AI to understand a project. It reads 30+ files at full length — each one consuming thousands of tokens. By the time it has enough context to help, your window is half gone.

With Field Agent27–58% saved

File reads return compressed summaries. The AI gets the structure and key symbols without consuming the raw source.

Debugging a failing build

You paste 200 lines of build output. The AI reads the full error log, then reads the source files mentioned in the errors. A single debug cycle can consume 50K+ tokens.

With Field Agent30–60% saved

Build output is compressed to just the actual errors. Source files are summarised. The AI diagnoses faster with less noise.

Pasting logs or stack traces

You copy-paste server logs or a crash report into your prompt. 200 lines of timestamped output enters your context at full size — most of it irrelevant.

With Field Agent50–94% saved

Large inline content is detected and compressed before it reaches the AI. 200 lines become a 2-line summary with the key finding.

Multi-file refactoring

Renaming a function across 15 files. The AI reads every file, understands the dependencies, makes changes, then reads them again to verify. Each round-trip multiplies token usage.

With Field Agent25–50% saved

The AI gets symbol maps and structural summaries instead of reading every file in full. Only the files being edited are read verbatim.

Running tests and type checks

You run the test suite. 500 lines of test output, most of it passing tests. The AI processes all of it to find the 3 failures buried in the noise.

With Field Agent30–60% saved

Test and typecheck output is compressed to failures only. The AI immediately sees what broke and where.

Reviewing a pull request

You ask the AI to review a diff. It reads the full diff, then reads every modified file for context. A 20-file PR can consume 100K+ tokens before the review even starts.

With Field Agent30–55% saved

Diffs are compressed to per-file change summaries. Context files are summarised. The AI focuses on what changed and why, not raw line-by-line content.

Savings ranges are from measured benchmarks on real TypeScript codebases using Claude Opus 4.6 + Field Agent. Each scenario run multiple times with and without Field Agent to establish the range. Actual results vary with codebase size and complexity.

Key feature

Large file summarization at scale

File reads are the single biggest context consumer in AI-assisted coding. A typical session reads 20-50 files — each one eating into your context window. Field Agent intercepts these reads and returns a structured summary instead. The bigger the file, the bigger the savings.

File sizeExampleWithout FAWith FATokens saved
50 linesSmall utility4,2003,40019%
100 linesModule7,8005,60028%
250 linesRoute handler16,50010,90034%
500 linesService class31,00018,20041%
1,000 linesLarge module58,40028,70051%
2,000 linesMonolith file112,00048,30057%
5,000 linesGenerated / bundle274,00092,50066%

What the summary includes

Always returned

  • One-paragraph purpose summary
  • Key exported symbols with signatures
  • Import dependencies (internal + external)
  • Line count and token estimate

With focus query

  • Relevant sections with line ranges
  • Focused analysis on the specific topic
  • Related symbols and call sites
  • Suggestions for which sections to read in full

The summary is typically 15-30 lines regardless of file size. For a 2,000-line file, that's a 98%+ reduction in context consumed. Claude can always request the full file (or a specific line range) if the summary isn't enough.

Figures shown are illustrative projections based on early benchmarks and will be replaced with verified benchmark data before launch. Actual savings will vary by file complexity and content type.

Key feature

Build and test output compression

A failing build dumps hundreds of lines of output into your context. Most of it is noise — passing tests, dependency resolution, compilation progress. Your AI only needs the actual errors. Field Agent strips the noise and delivers just the signal.

ScenarioRaw outputAfter compressionTokens saved
TypeScript build (3 errors in 200 files)18,4002,10089%
Jest test suite (5 failures in 120 tests)24,6004,80080%
ESLint run (12 warnings, 2 errors)8,2001,90077%
Docker build (layer cache miss)15,3003,20079%
CI pipeline log (full run)42,0005,50087%

Figures shown are illustrative projections and will be replaced with verified benchmark data before launch. Actual compression depends on output verbosity and error density.

Key feature

Log and error triage

Developers paste server logs, crash reports, and stack traces directly into their prompts every day. A single paste can add 5,000-50,000 tokens of raw text — most of which is timestamp noise and repetitive log lines. Field Agent finds the signal and discards the rest.

Content pastedRaw tokensAfter compressionTokens saved
200 lines of server logs (OOM crash)5,20030094%
Node.js stack trace (unhandled rejection)1,80035081%
500 lines of nginx access logs14,50080094%
Kubernetes pod crash loop logs8,9001,20087%
Python traceback with dependency chain3,20045086%
Mixed: stack trace + 100 log lines + JSON error12,4001,10091%

Figures shown are illustrative projections and will be replaced with verified benchmark data before launch. Actual savings depend on log density and content structure.

Key feature

Code review and PR analysis

Reviewing a pull request with AI means reading every modified file plus the diff itself. A 20-file PR can consume over 100K tokens before the review even begins. Field Agent compresses diffs and context files so your AI focuses on what changed.

PR scopeWithout FAWith FATokens saved
Small PR (3 files, 50 lines changed)12,4007,80037%
Medium PR (10 files, 200 lines changed)48,00024,50049%
Large PR (25 files, 600 lines changed)118,00052,00056%
Refactor PR (40 files, renames + moves)185,00072,00061%
Dependency upgrade (15 files + lockfile)92,00038,00059%

Figures shown are illustrative projections and will be replaced with verified benchmark data before launch. Actual savings depend on PR complexity and file sizes.

Why use Field Agent

40-94%measured token savings

Save 40-94% tokens on data

File reads, pasted logs, build output, stack traces — Field Agent compresses everything via a secondary model before it reaches your primary AI. Measured savings of 40%+ on tool output, and 50-94% on inline content.

2xmore headroom per session

Extend your context window

By compressing file reads, tool output, and inline content via a secondary model, you can work on complex tasks for longer without hitting context limits or triggering compaction.

<2savg response time

Faster tool calls

File reads, grep results, log analysis, build triage, and typechecking are handled by a lightweight secondary model — not your primary AI. Local or cloud, extraction is fast.

17tools included

Works with any MCP client

Claude Code, Cursor, Windsurf, Continue, or any tool that supports MCP. Layer 1 works everywhere. Layer 2 adds even deeper savings when using GooDex.

Estimate your savings

Select your LLM provider, model, team size, and expected token reduction to see how much Field Agent could save your team each month and year.

5

What do you typically use AI for? (select all that apply)

Estimated token savings:2756%based on 3 selected task types

Current monthly spend

$788

155M in + 22M out

Monthly savings

$213$441

2756% fewer tokens

With Field Agent

$346 $575

per month

RecommendedField Agent Basic$49/mo × 5 seats = $245/mo
net: $0$196/mo

Claude Sonnet 4: $3/MTok input, $15/MTok output

power user estimate · 5 licences required

Token usage estimates are based on a power-user profile (~8 hours/day of AI-assisted coding). Savings ranges are from measured benchmarks and engineering estimates per task type. Actual results will vary with file sizes, codebase complexity, and usage patterns. API prices reflect standard rates as of April 2026.

17 tools, zero configuration

Field Agent registers these tools automatically. Your AI assistant discovers and uses them when they'll save context. Three categories: core extraction, code intelligence, and CLI proxies that run commands and return compressed output.

Core extraction (7)

summarize_file

Read and summarize files via a secondary model — Claude sees a 20-line summary instead of 500 lines.

summarize_content

Compress large text blocks (logs, docs, command output) to their essence.

analyze_web_page

Fetch a URL and extract only what's relevant to your question.

triage_build_output

Parse verbose build or test output and return just the actual errors.

analyze_logs

Find errors and warnings in large logs related to a specific issue.

grep_filter

Re-rank search results by relevance — no more scrolling through noise.

validate_patch

Check if a patch target exists before editing — prevents the fail-retry cycle.

Code intelligence (5)

extract_symbols

Extract all exported functions, classes, types, and constants from a file.

summarize_diff

Compress a git diff into a per-file change summary with impact analysis.

summarize_directory

Scan a directory structure and produce an architecture overview.

classify_error

Classify an error by type and severity, suggest likely cause and fix.

summarize_test_results

Parse test runner output — extract pass/fail counts and failing test names.

CLI proxies (5)

git_diff_summary

Run git diff and return a compressed summary of changes.

git_log_summary

Run git log and return a compressed commit history.

build_run

Run the build command and return only errors and warnings.

test_run

Run tests and return a compressed pass/fail summary.

typecheck_run

Run the TypeScript typechecker and return only the errors.

How it works

Field Agent operates at two levels. Layer 1 optimises tool output — works with any MCP client. Layer 2 optimises your prompt content before it reaches the cloud — maximum savings.

Your prompt(files, logs, code, questions)
Layer 2: Content Optimisation
Detects large content in your prompt → compresses via secondary model → sends compact version
Cloud LLM(Claude, GPT, Gemini, etc.)
▼ tool call
Layer 1: Tool Optimisation
Compresses tool output (file reads, search results, command output) before it enters context
Secondary model
+
Your files
Basic: Ollama on your machinePro: Our cloud — no local setup
Layer 2 saves 50-94% on inline contentLayer 1 saves 27-58% on tool output

Layer 1: Tool output optimisation

1. Your AI requests a 500-line file

2. Field Agent compresses it to a 20-line summary

3. Your AI uses the summary to reason

4. Requests full content only when needed

Savings: 27-58% on tool output

Layer 2: Content optimisation

1. You paste 200 lines of logs into your prompt

2. Field Agent detects and compresses it

3. Your AI receives a 2-line summary instead

4. Full content available on demand

Savings: 50-94% on inline content

New

Layer 2: Content optimisation

When you paste logs, build output, stack traces, or code into your prompt, it enters the AI's context at full size. Layer 2 catches this content before it reaches the cloud — compresses it via a secondary model and sends a compact version to your primary AI. The full content remains available on demand.

// Example: 200 lines of server logs pasted into prompt

1. Field Agent detects large content in your prompt

2. Compresses via secondary model

3. Your AI receives: "OOM at 92% memory, npm install timeout"

4. Full content available if the AI needs more detail

Result: 5,200 → 300 tokens (94% savings)

Content types handled

Code blocksLarge code snippets
Stack tracesError output and frames
Log blocksServer and application logs
Git diffsChange sets and patches
JSON / XMLStructured data payloads
Build outputCompiler and test failures
API responsesHTTP responses and bodies
Config filesYAML, TOML, and dotfiles
And moreAny large text content

Two layers, two levels of savings

Layer 1: Tool optimisation (any client)

  • Compressed file reads
  • Compressed command and search output
  • Intelligent escalation to full content when needed

Saves 27-58% on tool output

Layer 2: Content optimisation

  • Everything in Layer 1, plus:
  • Automatic detection and compression of inline content
  • Full content available on demand

Saves 50-94% on inline content

Why not just...

There are other ways to deal with context limits. Here's how they compare to Field Agent's compression-first approach.

ApproachHow it worksLimitationsField Agent
Use a bigger context windowModels like Claude (200K) or Gemini (1M+) accept more tokensMore tokens = higher cost and slower responses. Attention quality degrades with length. Doesn't reduce spend.Reduces what enters the window, so you get more useful work per token regardless of window size
Prompt cachingCache repeated prefixes (system prompt, tool definitions) for 50-90% input discountOnly saves on repeated content. New file reads, search results, and inline content are never cached.Compresses the non-cacheable parts — file reads, tool output, pasted content. Stacks with prompt caching.
Summarise manuallyCopy-paste file contents into a separate tool, summarise, paste backBreaks flow. Time-consuming. You still consume tokens to summarise. Doesn't scale to 20-50 file reads per session.Automatic — intercepts tool calls and compresses inline. Zero manual effort, works on every file read.
Read less codeOnly read the specific lines you need, not whole filesRequires knowing which lines matter before you read them. The AI often reads full files to understand context.Compressed reads give the AI enough context to decide what to read in full — only escalates when needed.
Reference files instead of including themTell the AI "look at src/auth.ts" instead of pasting its contentThe AI still reads the full file to follow the reference — every line enters the context window. Multiple references compound quickly.References are intercepted automatically. The AI receives a compressed summary and only fetches full content for the specific sections it needs.
Use a cheaper modelSwitch from Opus/GPT-4 to Haiku/GPT-4-mini for routine tasksLower quality output. Smaller models struggle with complex multi-file reasoning. Manual model switching.Keep your best model for reasoning. Field Agent handles the data-heavy extraction on a lightweight secondary model — locally or in our cloud.

Field Agent is complementary to these approaches — it stacks with prompt caching, works with any context window size, and runs alongside any model. The savings compound.

Works with every language

Field Agent compresses code, logs, and tool output regardless of language. These are the languages and frameworks we officially test and optimise for — but it works with any programming language your AI assistant supports.

TypeScriptTypeScript
JavaScriptJavaScript
PythonPython
JavaJava
GoGo
RustRust
C#C#
RubyRuby
PHPPHP
SwiftSwift
KotlinKotlin
ReactReact
Next.jsNext.js
VueVue
AngularAngular
Node.jsNode.js
C / C++C / C++

This is not an exhaustive list. Field Agent's compression works at the text and structure level, so any language or framework supported by your AI assistant will benefit. We continuously add language-specific optimisations based on user demand.

Set up in minutes

One command or config change. Field Agent works with any MCP-compatible client — pick your platform below.

Claude Code

Run this command

claude mcp add field-agent -- npx -y @goodex/field-agent-mcp

Restart your session after adding. Field Agent is immediately available.

The MCP server handles all setup automatically. No manual model downloads or configuration required.

Pays for itself from day one

Field Agent typically saves 40-94% on cloud AI token costs. A team of 5 developers on Claude Code saves $400-800/month — the subscription pays for itself many times over. Start with a 14-day free trial.

40-94%

measured token savings

$80-120

saved/month per developer

10-20x

typical ROI on Basic plan

Basic

$49/month

or $490/year (2 months free)

Core extraction tools powered by Ollama on your machine. Saves $80-120/month on a typical Claude or GPT workflow.

Start 14-day free trial

No credit card required

What's included

  • 10M tokens / month
  • 7 core extraction tasks
  • Smart file reads
  • 4 lifecycle hooks
  • All MCP clients supported
  • Local mode (Ollama on your machine)
  • Code intelligence tools
  • CLI proxy tools
Most popular

Pro

$149/month

or $1,490/year (2 months free)

Full tool suite with cloud-hosted inference — no local Ollama required. Typically saves $400-1,600/month on team AI spend.

Start 14-day free trial

No credit card required

Everything in Basic, plus

  • 100M tokens / month
  • All 19 tasks
  • All 8 lifecycle hooks
  • Code intelligence (extract_symbols, summarize_diff, etc.)
  • CLI proxies (build, test, typecheck, git)
  • Cloud mode (no local setup required)
  • Priority support
  • Overage: $10 per 10M tokens

Enterprise

From $49/user/month

volume discounts at 50+ and 100+ seats

Unlimited tokens, custom tasks, SLA, and dedicated support for teams saving $8,000+/month on AI spend. Built on patent-pending technology.

Contact sales

Everything in Pro, plus

  • Unlimited tokens
  • All tasks + custom task types
  • All hooks + custom hooks
  • Team management & admin controls
  • Dedicated support & SLA
  • On-premise deployment option
  • SSO & audit logs
FeatureBasicProEnterprise
Price$49/mo$149/moFrom $49/user/mo
Annual price$490/yr$1,490/yrCustom
Monthly token limit10M100MUnlimited
Overage pricing$10 / 10M tokensVolume rates
Core extraction tasks (7)
Code intelligence tasks (5)
CLI proxy tasks (5)
Custom task types
Smart file reads
Lifecycle hooks4 basicAll 8All + custom
MCP client support
Local mode (Ollama)
Cloud mode (no local setup)
Priority support
Team management
SSO & audit logs
On-premise deployment
SLA

All plans include a 14-day free trial. Token limits reset monthly. Annual billing saves 2 months. Enterprise volume discounts available at 50+ and 100+ seats.

Start saving tokens today

Free tier includes 5M tokens/month. No credit card required.

Frequently asked questions

Does Field Agent slow down my workflow?+

In local mode, inference adds 1-3 seconds per tool call on Apple Silicon. In cloud mode (Pro/Enterprise), latency is comparable. But because Field Agent reduces total tokens consumed, your overall session is often faster — fewer round-trips to the primary AI, fewer compaction events, and the AI reaches answers in fewer turns. Benchmarks show the net effect is neutral to positive on wall-clock time.

Does my code leave my machine?+

In local mode (Basic), nothing leaves your machine. Your files are read and summarised by Ollama on your hardware — only the compressed summary reaches your primary AI. In cloud mode (Pro/Enterprise), file content is sent to our secure API for processing via a lightweight secondary model. Content is processed in memory and never stored or logged.

What happens if the secondary model is unavailable?+

Field Agent degrades gracefully. In local mode, if Ollama is unreachable or the model isn't available, it falls back to standard tool behaviour. In cloud mode, our infrastructure handles availability. Either way, your AI assistant reads files and processes output directly — just without the compression. No errors, no broken workflows.

Does it work with my IDE / AI tool?+

Field Agent works with any tool that supports the Model Context Protocol (MCP): Claude Code, Claude Desktop, Cursor, VS Code (Copilot), Windsurf, Gemini CLI, and more. Layer 1 (tool optimisation) works everywhere. Layer 2 (content optimisation) provides additional savings and will expand to more platforms.

How accurate are the file summaries?+

Summaries include the file's purpose, key exported symbols with type signatures, import dependencies, and line count. On our benchmark suite, qwen3:8b scores 86/100 on summary quality across 14 task types. Claude can always request the full file or a specific line range if the summary isn't sufficient — this happens in roughly 15-20% of cases.

Can I use my own local model?+

Yes, on the Basic plan. Field Agent works with any Ollama model. We benchmark and recommend qwen3:8b for the best speed/quality balance (86/100, 25 tok/s on M4 Pro), but qwen3:14b (88/100), gemma3:12b (90/100), and even qwen3:1.7b (81/100, 75 tok/s) all work. On Pro/Enterprise, our cloud-hosted model is pre-configured — no local setup needed.

What's the difference between Basic and Pro?+

Basic ($49/mo) gives you the 7 core extraction tools running locally via Ollama, with 10M tokens/month. Pro ($149/mo) unlocks all 19 tools including code intelligence, CLI proxies, and cloud-hosted inference — no local model or GPU required. Pro includes 100M tokens/month and priority support. Both include a 14-day free trial.

How do token limits work with a subscription plan like Claude Max?+

If you're on a fixed subscription (Claude Pro, Max, Teams, Cursor, Copilot), you have a set token allowance. Field Agent makes each token go further — with 40% savings, your 1M token allowance effectively becomes 1.7M tokens of work. You get longer sessions, fewer compaction events, and more headroom before hitting limits. Use our savings calculator to see the exact multiplier for your plan.

Release notes

Field Agent is under active development. Here's what's new.

v1.3April 2026

Cloud mode

Full-cloud inference — no local model or GPU required. Available on Pro and Enterprise plans.

Three operational modes

Choose local, partial-cloud, or full-cloud depending on your privacy and performance needs.

Tiered access control

Basic, Pro, and Enterprise tiers with different tool and token allowances.

Usage tracking

Per-user token consumption tracking with monthly quota management.

v1.2March 2026

Consolidated MCP interface

Single dispatch tool replaces 10 individual tools — 68% less schema overhead, faster tool discovery.

Editor lifecycle integration

8 hooks for automatic optimisation of tool output, prompts, and context across your coding session.

Large file handling

Improved compression for files of any size, with automatic chunking for very large files.

Code intelligence tools

5 new tasks: symbol extraction, diff compression, directory summaries, error classification, test result parsing.

CLI proxy tools

5 new tasks: compressed output from git, build, test, typecheck, and lint commands.

v1.0February 2026

Initial release

7 core extraction tasks: file summarisation, content compression, web analysis, build triage, log analysis, search filtering, patch validation.

MCP server

Works with Claude Code, Cursor, VS Code, Windsurf, Gemini CLI, and any MCP-compatible client.

Smart file reads

File reads return compressed summaries by default, with full content available on demand.

Intelligent escalation

AI receives compressed data first and seamlessly requests more detail when needed.

Stop wasting context on data

Let a secondary model handle the heavy lifting. Your primary AI does the thinking.