Agent Toolbox

26 deterministic, offline pre-action safety gates for AI agents, each with a signed verdict.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

Not yet automatically verified

We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag — we're steadily working through the catalog.

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "agent-toolbox": {
      "command": "npx",
      "args": [
        "-y",
        "agentoolbox-mcp"
      ]
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Documentation Overview

agent-toolbox.ai

The quality layer for AI agents. 26 deterministic, offline pre-action gates across 6 suites — verify, secure, and validate agent actions before they happen — callable by any agent, paid autonomously in SOL.

API: https://api.agent-toolbox.ai
Website: agent-toolbox.ai
GitHub: solhammer/agentoolbox
Wiki: Design & how we build tools for agents

Quick start
Service overview
API reference
Authentication & SOL payments
Integration patterns
MCP integration
TypeScript SDK
Self-hosting
Roadmap

Quick start (30 seconds)

No signup. No API key. First 10 calls per IP are free.

server.ts

# Discover pricing and service wallet — start here
curl https://api.agent-toolbox.ai/v1/pricing

# Validate AI-generated imports
curl -X POST https://api.agent-toolbox.ai/v1/validate/imports \
  -H "Content-Type: application/json" \
  -d '{"language":"python","code":"import numpy\nfrom superlogger import magic_log"}'

# Run the hallucination firewall
curl -X POST https://api.agent-toolbox.ai/v1/verify \
  -H "Content-Type: application/json" \
  -d '{"outputType":"code","language":"python","llmResponse":"import numpy\nfrom ghostpkg import magic","enforcementMode":"block"}'

Service overview

26 tools across 6 suites. Every verdict is deterministic and offline (unless a tool documents an opt-in networked mode). Call GET /v1/pricing (free) to self-discover the wallet and per-endpoint rates. Full request/response schemas live in openapi.json (served at GET /openapi.json) and on agent-toolbox.ai; see the roadmap for what's shipped and planned.

1 SOL = 10,000 credits · Free tier: 10 calls/IP, no auth.

Core quality

Endpoint	Purpose	Credits	Latency
`POST /v1/validate/imports`	Check AI package imports against live registries	1	<200ms
`POST /v1/verify`	Hallucination firewall — PASS/FLAG/BLOCK	2	<500ms
`POST /v1/distill`	Compress conversation context to a token budget	1	<50ms

Security

Endpoint	Purpose	Credits	Latency
`POST /v1/scan/secrets`	Detect hardcoded credentials in code	1	<10ms
`POST /v1/scan/injection`	Detect prompt injection in user input	1	<10ms
`POST /v1/tokens/count`	Count tokens + estimate cost before an LLM call	1	<10ms
`POST /v1/scan/vulnerabilities`	Check packages against the OSV/CVE database	2	<500ms
`POST /v1/scan/pii`	Detect & redact PII/PHI/PCI before egress	1	<20ms
`POST /v1/scan/command`	Flag destructive shell commands before execution	1	<5ms
`POST /v1/scan/url`	Block SSRF / egress-policy violations before a fetch	1	<5ms

Finance

Endpoint	Purpose	Credits	Latency
`POST /v1/finance/units`	Validate raw vs UI token amount (decimal safety)	1	<10ms
`POST /v1/finance/price`	Cross-source price validation	2	~300ms
`POST /v1/finance/symbol`	Resolve ticker / token identity	1	~200ms
`POST /v1/finance/token/risk`	Rug-pull / mint & freeze authority scan	3	~500ms
`POST /v1/finance/slippage`	Pool depth / price-impact estimate	2	~200ms
`POST /v1/finance/order/risk`	Composite pre-trade gate (runs all checks)	5	~500ms
`POST /v1/finance/position/check`	Deterministic position limits + kill-switch	1	<1ms

Compliance & health

Endpoint	Purpose	Credits	Latency
`POST /v1/compliance/sanctions`	Screen names against OFAC SDN + Consolidated	1	<10ms
`POST /v1/health/rx-check`	Medication unit / overdose / interaction gate	2	<10ms

Agent · infra · legal

Endpoint	Purpose	Credits	Latency
`POST /v1/agent/tool-args`	Validate tool-call args against schema + policy	1	<5ms
`POST /v1/infra/plan/risk`	Static IaC blast-radius gate (Terraform / IAM / K8s)	2	<10ms
`POST /v1/legal/cite`	Validate US case citations + quote fidelity	2	<5ms
`POST /v1/legal/deadline`	Court / calendar deadline math	1	<5ms

Data & validation

Endpoint	Purpose	Credits	Latency
`POST /v1/validate/identifier`	Checksum-validate IBAN / card / VIN / NPI / …	1	<5ms
`POST /v1/validate/schema`	Validate JSON against a JSON Schema (Draft-07)	1	<5ms
`POST /v1/scan/sql`	Flag destructive / injection-prone SQL	1	<5ms

API reference

Detailed request/response docs for the core endpoints follow. The Security, Compliance, Health, Agent, Infra, Legal, and Data suites are fully specified in openapi.json and on agent-toolbox.ai.

`GET /v1/pricing`

Agents should call this first to self-discover the service wallet and per-endpoint rates before making a payment.

Terminal

curl https://api.agent-toolbox.ai/v1/pricing

config.json

{
  "wallet": "8qXedRydihKEETqU64UXtG2sYZaUhwR4HBFz4Suu27CV",
  "network": "mainnet-beta",
  "endpoints": {
    "/v1/validate/imports":    { "credits": 1, "lamports": 100000, "sol": 0.0001, "usdApprox": "~$0.015" },
    "/v1/verify":              { "credits": 2, "lamports": 200000, "sol": 0.0002, "usdApprox": "~$0.030" },
    "/v1/distill":             { "credits": 1, "lamports": 100000, "sol": 0.0001, "usdApprox": "~$0.015" },
    "/v1/scan/secrets":        { "credits": 1, "lamports": 100000, "sol": 0.0001, "usdApprox": "~$0.015" },
    "/v1/scan/injection":      { "credits": 1, "lamports": 100000, "sol": 0.0001, "usdApprox": "~$0.015" },
    "/v1/tokens/count":        { "credits": 1, "lamports": 100000, "sol": 0.0001, "usdApprox": "~$0.015" },
    "/v1/scan/vulnerabilities": { "credits": 2, "lamports": 200000, "sol": 0.0002, "usdApprox": "~$0.030" }
  },
  "conversion": { "solPerCredit": 0.0001, "creditsPerSol": 10000 },
  "freeTier": { "calls": 10, "auth": false },
  "howToPay": [
    "1. Send SOL to: 8qXedRydihKEETqU64UXtG2sYZaUhwR4HBFz4Suu27CV",
    "2. Pass the transaction signature as your Bearer token on the first call",
    "3. Credits are verified on-chain and added to your account",
    "4. Subsequent calls deduct credits automatically"
  ]
}

`POST /v1/validate/imports`

Checks every import in AI-generated code against live package registries in parallel. 19.7% of AI-generated packages don't exist (USENIX 2025).

Languages: python · javascript · typescript · rust · go

Request:

config.json

{
  "language": "python",
  "code": "import numpy\nfrom ghostpkg import magic\nimport pandas",
  "timeoutMs": 5000
}

Response:

config.json

{
  "language": "python",
  "valid": [
    { "name": "numpy", "status": "valid", "registry": "pypi", "registryUrl": "https://pypi.org/pypi/numpy/json" },
    { "name": "pandas", "status": "valid", "registry": "pypi" }
  ],
  "hallucinated": [
    { "name": "ghostpkg", "status": "hallucinated", "registry": "pypi", "registryUrl": "https://pypi.org/pypi/ghostpkg/json" }
  ],
  "unknown": [],
  "totalImports": 3,
  "hallucinationRate": 0.33,
  "latencyMs": 142
}

`POST /v1/verify`

Full hallucination firewall. Runs all check layers in parallel. Returns a signed verdict.

Request:

config.json

{
  "outputType": "code",
  "llmResponse": "import numpy\nfrom ghostpkg import magic",
  "language": "python",
  "enforcementMode": "block",
  "sourceTexts": ["optional: retrieved context docs for NLI grounding"],
  "timeoutMs": 5000
}

Field	Type	Values	Default
`outputType`	string	`code` `natural_language` `agent_action` `factual_claim`	required
`enforcementMode`	string	`block` `flag` `audit`	`block`
`language`	string	`python` `javascript` `typescript` `rust` `go`	required for `code`
`sourceTexts`	string[]	Retrieved docs to ground NLI check against	—

Response:

config.json

{
  "verdict": "BLOCK",
  "overallScore": 0.0,
  "claims": [
    {
      "text": "from ghostpkg import magic",
      "verdict": "BLOCK",
      "confidence": 0.95,
      "checkType": "hallucinated_package",
      "evidence": "Package \"ghostpkg\" not found in pypi",
      "suggestedFix": "Remove or replace \"ghostpkg\" with a real package."
    }
  ],
  "certificate": "sha256:1cea7cf643339ac7054a285...",
  "latencyMs": 187
}

Verdict meanings:

PASS — no issues, safe to use
FLAG — potential issue, human review recommended
BLOCK — confirmed problem, do not use

Check types:

`checkType`	Verdict	Triggered by
`hallucinated_package`	BLOCK	Import not in live registry
`url_not_found`	BLOCK	URL returns 404/410
`url_unreachable`	FLAG	URL request timed out
`malformed_doi`	FLAG	DOI doesn't match `10.NNNN/suffix`
`malformed_arxiv_id`	FLAG	arXiv ID doesn't match known formats
`numeric_contradiction`	FLAG	Percentage >100% or contradictory language
`low_nli_consistency`	FLAG/BLOCK	Vectara HHEM score below threshold

`POST /v1/distill`

Compresses conversation history to a token budget using TF-IDF importance scoring. Always preserves the system prompt. Deduplicates consecutive identical messages. Retains the most recent and most important content when truncating.

Request:

config.json

{
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "..." },
    { "role": "assistant", "content": "..." }
  ],
  "targetTokens": 4000,
  "preserveSystemPrompt": true
}

Read the full README →View source on GitHub →

Related MCP Servers

View all in Developer Tools View all alternatives

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Agent Toolbox

Add the following block to your claude_desktop_config.json under mcpServers: "mcpServers": { "agent-toolbox": { "command": "npx", "args": ["-y", "Agent Toolbox"] } }

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/agent-toolbox?style=directory)](https://allmcps.com/mcp/agent-toolbox)

HTML Embed

<a href="https://allmcps.com/mcp/agent-toolbox"><img src="https://allmcps.com/api/badge/agent-toolbox?style=directory" alt="Agent Toolbox on AllMCPs" /></a>

Technical Specs & Signals

CategoryDeveloper Tools

36Quality signal: Fair · 36/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20

Documentation & tools16/30

Adoption & activity1/15

Community engagement0/10

A guidance signal from public completeness & health data — not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.

★ Spotlight Slot

Feature Your MCP Server

Get maximum visibility for your server across our directory, search results, and detail pages.

Spotlight Your Server

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to unlock edit access and the Official badge — proof is checked automatically, then reviewed by our team.

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 💻 Developer Tools →Best MCP servers for Developers →Alternatives to Agent Toolbox →Install in Claude Desktop Install in Cursor Install in VS Code

Agent Toolbox

26 deterministic, offline pre-action safety gates for AI agents, each with a signed verdict.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

Not yet automatically verified

We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag — we're steadily working through the catalog.

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "agent-toolbox": {
      "command": "npx",
      "args": [
        "-y",
        "agentoolbox-mcp"
      ]
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Documentation Overview

agent-toolbox.ai

API: https://api.agent-toolbox.ai
Website: agent-toolbox.ai
GitHub: solhammer/agentoolbox
Wiki: Design & how we build tools for agents

Quick start
Service overview
API reference
Authentication & SOL payments
Integration patterns
MCP integration
TypeScript SDK
Self-hosting
Roadmap

Quick start (30 seconds)

No signup. No API key. First 10 calls per IP are free.

server.ts

# Discover pricing and service wallet — start here
curl https://api.agent-toolbox.ai/v1/pricing

# Validate AI-generated imports
curl -X POST https://api.agent-toolbox.ai/v1/validate/imports \
  -H "Content-Type: application/json" \
  -d '{"language":"python","code":"import numpy\nfrom superlogger import magic_log"}'

# Run the hallucination firewall
curl -X POST https://api.agent-toolbox.ai/v1/verify \
  -H "Content-Type: application/json" \
  -d '{"outputType":"code","language":"python","llmResponse":"import numpy\nfrom ghostpkg import magic","enforcementMode":"block"}'

Service overview

1 SOL = 10,000 credits · Free tier: 10 calls/IP, no auth.

Core quality

Endpoint	Purpose	Credits	Latency
`POST /v1/validate/imports`	Check AI package imports against live registries	1	<200ms
`POST /v1/verify`	Hallucination firewall — PASS/FLAG/BLOCK	2	<500ms
`POST /v1/distill`	Compress conversation context to a token budget	1	<50ms

Security

Endpoint	Purpose	Credits	Latency
`POST /v1/scan/secrets`	Detect hardcoded credentials in code	1	<10ms
`POST /v1/scan/injection`	Detect prompt injection in user input	1	<10ms
`POST /v1/tokens/count`	Count tokens + estimate cost before an LLM call	1	<10ms
`POST /v1/scan/vulnerabilities`	Check packages against the OSV/CVE database	2	<500ms
`POST /v1/scan/pii`	Detect & redact PII/PHI/PCI before egress	1	<20ms
`POST /v1/scan/command`	Flag destructive shell commands before execution	1	<5ms
`POST /v1/scan/url`	Block SSRF / egress-policy violations before a fetch	1	<5ms

Finance

Endpoint	Purpose	Credits	Latency
`POST /v1/finance/units`	Validate raw vs UI token amount (decimal safety)	1	<10ms
`POST /v1/finance/price`	Cross-source price validation	2	~300ms
`POST /v1/finance/symbol`	Resolve ticker / token identity	1	~200ms
`POST /v1/finance/token/risk`	Rug-pull / mint & freeze authority scan	3	~500ms
`POST /v1/finance/slippage`	Pool depth / price-impact estimate	2	~200ms
`POST /v1/finance/order/risk`	Composite pre-trade gate (runs all checks)	5	~500ms
`POST /v1/finance/position/check`	Deterministic position limits + kill-switch	1	<1ms

Compliance & health

Endpoint	Purpose	Credits	Latency
`POST /v1/compliance/sanctions`	Screen names against OFAC SDN + Consolidated	1	<10ms
`POST /v1/health/rx-check`	Medication unit / overdose / interaction gate	2	<10ms

Agent · infra · legal

Endpoint	Purpose	Credits	Latency
`POST /v1/agent/tool-args`	Validate tool-call args against schema + policy	1	<5ms
`POST /v1/infra/plan/risk`	Static IaC blast-radius gate (Terraform / IAM / K8s)	2	<10ms
`POST /v1/legal/cite`	Validate US case citations + quote fidelity	2	<5ms
`POST /v1/legal/deadline`	Court / calendar deadline math	1	<5ms

Data & validation

Endpoint	Purpose	Credits	Latency
`POST /v1/validate/identifier`	Checksum-validate IBAN / card / VIN / NPI / …	1	<5ms
`POST /v1/validate/schema`	Validate JSON against a JSON Schema (Draft-07)	1	<5ms
`POST /v1/scan/sql`	Flag destructive / injection-prone SQL	1	<5ms

API reference

Detailed request/response docs for the core endpoints follow. The Security, Compliance, Health, Agent, Infra, Legal, and Data suites are fully specified in openapi.json and on agent-toolbox.ai.

`GET /v1/pricing`

Agents should call this first to self-discover the service wallet and per-endpoint rates before making a payment.

Terminal

curl https://api.agent-toolbox.ai/v1/pricing

config.json

{
  "wallet": "8qXedRydihKEETqU64UXtG2sYZaUhwR4HBFz4Suu27CV",
  "network": "mainnet-beta",
  "endpoints": {
    "/v1/validate/imports":    { "credits": 1, "lamports": 100000, "sol": 0.0001, "usdApprox": "~$0.015" },
    "/v1/verify":              { "credits": 2, "lamports": 200000, "sol": 0.0002, "usdApprox": "~$0.030" },
    "/v1/distill":             { "credits": 1, "lamports": 100000, "sol": 0.0001, "usdApprox": "~$0.015" },
    "/v1/scan/secrets":        { "credits": 1, "lamports": 100000, "sol": 0.0001, "usdApprox": "~$0.015" },
    "/v1/scan/injection":      { "credits": 1, "lamports": 100000, "sol": 0.0001, "usdApprox": "~$0.015" },
    "/v1/tokens/count":        { "credits": 1, "lamports": 100000, "sol": 0.0001, "usdApprox": "~$0.015" },
    "/v1/scan/vulnerabilities": { "credits": 2, "lamports": 200000, "sol": 0.0002, "usdApprox": "~$0.030" }
  },
  "conversion": { "solPerCredit": 0.0001, "creditsPerSol": 10000 },
  "freeTier": { "calls": 10, "auth": false },
  "howToPay": [
    "1. Send SOL to: 8qXedRydihKEETqU64UXtG2sYZaUhwR4HBFz4Suu27CV",
    "2. Pass the transaction signature as your Bearer token on the first call",
    "3. Credits are verified on-chain and added to your account",
    "4. Subsequent calls deduct credits automatically"
  ]
}

`POST /v1/validate/imports`

Checks every import in AI-generated code against live package registries in parallel. 19.7% of AI-generated packages don't exist (USENIX 2025).

Languages: python · javascript · typescript · rust · go

Request:

config.json

{
  "language": "python",
  "code": "import numpy\nfrom ghostpkg import magic\nimport pandas",
  "timeoutMs": 5000
}

Response:

config.json

{
  "language": "python",
  "valid": [
    { "name": "numpy", "status": "valid", "registry": "pypi", "registryUrl": "https://pypi.org/pypi/numpy/json" },
    { "name": "pandas", "status": "valid", "registry": "pypi" }
  ],
  "hallucinated": [
    { "name": "ghostpkg", "status": "hallucinated", "registry": "pypi", "registryUrl": "https://pypi.org/pypi/ghostpkg/json" }
  ],
  "unknown": [],
  "totalImports": 3,
  "hallucinationRate": 0.33,
  "latencyMs": 142
}

`POST /v1/verify`

Full hallucination firewall. Runs all check layers in parallel. Returns a signed verdict.

Request:

config.json

{
  "outputType": "code",
  "llmResponse": "import numpy\nfrom ghostpkg import magic",
  "language": "python",
  "enforcementMode": "block",
  "sourceTexts": ["optional: retrieved context docs for NLI grounding"],
  "timeoutMs": 5000
}

Field	Type	Values	Default
`outputType`	string	`code` `natural_language` `agent_action` `factual_claim`	required
`enforcementMode`	string	`block` `flag` `audit`	`block`
`language`	string	`python` `javascript` `typescript` `rust` `go`	required for `code`
`sourceTexts`	string[]	Retrieved docs to ground NLI check against	—

Response:

config.json

{
  "verdict": "BLOCK",
  "overallScore": 0.0,
  "claims": [
    {
      "text": "from ghostpkg import magic",
      "verdict": "BLOCK",
      "confidence": 0.95,
      "checkType": "hallucinated_package",
      "evidence": "Package \"ghostpkg\" not found in pypi",
      "suggestedFix": "Remove or replace \"ghostpkg\" with a real package."
    }
  ],
  "certificate": "sha256:1cea7cf643339ac7054a285...",
  "latencyMs": 187
}

Verdict meanings:

PASS — no issues, safe to use
FLAG — potential issue, human review recommended
BLOCK — confirmed problem, do not use

Check types:

`checkType`	Verdict	Triggered by
`hallucinated_package`	BLOCK	Import not in live registry
`url_not_found`	BLOCK	URL returns 404/410
`url_unreachable`	FLAG	URL request timed out
`malformed_doi`	FLAG	DOI doesn't match `10.NNNN/suffix`
`malformed_arxiv_id`	FLAG	arXiv ID doesn't match known formats
`numeric_contradiction`	FLAG	Percentage >100% or contradictory language
`low_nli_consistency`	FLAG/BLOCK	Vectara HHEM score below threshold

`POST /v1/distill`

Request:

config.json

{
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "..." },
    { "role": "assistant", "content": "..." }
  ],
  "targetTokens": 4000,
  "preserveSystemPrompt": true
}

Read the full README →View source on GitHub →

Related MCP Servers

View all in Developer Tools View all alternatives

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Agent Toolbox

Add the following block to your claude_desktop_config.json under mcpServers: "mcpServers": { "agent-toolbox": { "command": "npx", "args": ["-y", "Agent Toolbox"] } }

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/agent-toolbox?style=directory)](https://allmcps.com/mcp/agent-toolbox)

HTML Embed

<a href="https://allmcps.com/mcp/agent-toolbox"><img src="https://allmcps.com/api/badge/agent-toolbox?style=directory" alt="Agent Toolbox on AllMCPs" /></a>

Technical Specs & Signals

CategoryDeveloper Tools

36Quality signal: Fair · 36/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20

Documentation & tools16/30

Adoption & activity1/15

Community engagement0/10

★ Spotlight Slot

Feature Your MCP Server

Get maximum visibility for your server across our directory, search results, and detail pages.

Spotlight Your Server

Own this project?

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 💻 Developer Tools →Best MCP servers for Developers →Alternatives to Agent Toolbox →Install in Claude Desktop Install in Cursor Install in VS Code

Agent Toolbox

Quick Install

Client Config & Setup

Documentation Overview

agent-toolbox.ai

Contents

Quick start (30 seconds)

Service overview

Core quality

Security

Finance

Compliance & health

Agent · infra · legal

Data & validation

API reference

GET /v1/pricing

POST /v1/validate/imports

POST /v1/verify

POST /v1/distill

Related MCP Servers

Reviews

Frequently Asked Questions about Agent Toolbox

AllMCPs Directory Badge

Technical Specs & Signals

Feature Your MCP Server

Own this project?

Share & Embed

Explore more

Agent Toolbox

Quick Install

Client Config & Setup

Documentation Overview

agent-toolbox.ai

Contents

Quick start (30 seconds)

Service overview

Core quality

Security

Finance

Compliance & health

Agent · infra · legal

Data & validation

API reference

GET /v1/pricing

POST /v1/validate/imports

POST /v1/verify

POST /v1/distill

Related MCP Servers

Reviews

Frequently Asked Questions about Agent Toolbox

AllMCPs Directory Badge

Technical Specs & Signals

Feature Your MCP Server

Own this project?

Share & Embed

Explore more

`GET /v1/pricing`

`POST /v1/validate/imports`

`POST /v1/verify`

`POST /v1/distill`

`GET /v1/pricing`

`POST /v1/validate/imports`

`POST /v1/verify`

`POST /v1/distill`