Reuce hasta el 98 % de los tokens que tus agentes de IA gastan al usar herramientas MCP — sin perder nada.
Servidor | Herramientas | Antes | Después | Reducción |
filesystem (Anthropic) | 14 | 1892 tok | 236 tok | −88 % |
sequential-thinking | 1 | 926 tok | 20 tok | −98 % |
Google Calendr | 5 | 5010 tok | 660 tok | −87 % |
Entrprise (Cal + Gmail + Drve) | 12 | 8649 tok | 882 tok | −90 % |
sample_ap.js (JvScript) | — | 799 tok | 284 tok | −64.5 % |
sample_ap.ts (TypeScript) | — | 378 tok | 266 tok | −29.6 % |
ast_extractor.py (Pyhon) | — | 3633 tok | 890 tok | −75.5 % |
Menos tokens envíados = facturas de API más bajas, respuestas más rápidas. Y no se pierde nada. Cada comprobación confirma que las herramientas siguen siendo 100% usables tras la compresión.
Reproduce estos números tú mismo — cada entrada es un fijo estático en el repo, tokens contados con tiktoken cl00k_base:
python benchmarks/run_benchmark.py # the table above
python benchmarks/run_benchmark.py --json # machine-readable
python benchmarks/run_benchmark.py --fixture path/to/your_schemas.jsonRelated MCP server: Bifrost-MCP Gateway
Un a linea (macOS / Linux) — instala el paquete y configura Claude Desktop:
curl -sSL https://raw.githubusercontent.com/LoudiliMed/Refract/main/install-refract.sh | shPasar un script de internet a tu shell merece un vistazo rápido primero: inspectar instalar-refract.sh en GitHub. Nunca usa sudo.
O directamente con pip:
pip install refract-mcpExtras opcionales:
pip install refract-mcp[semantic] # semantic tool routing with embeddings
pip install refract-mcp[multilang] # JavaScript, TypeScript, JSX, TSX supportSe interpone entre tu agente y cualquier servidor MCP. Comprie los esquemas de las herramientas sobre la marcha para que tu agente no cargue el catálogo completo en cada petición.
Subproceso local (stdio):
refract-proxy --target "npx @modelcontextprotocol/server-filesystem /tmp" --verboseServidor remoto HTTP/SSE:
# --url implies SSE transport (explicit, recommended for remote endpoints)
refract-proxy --url https://my-mcp-server.com/sse
# or with --transport flag (auto-detection can be overridden)
refract-proxy --target https://my-mcp-server.com/sse --transport sseFlags del proxy:
Flag | Defecto | Descripción |
| requerido | Destino MCP: comando stdio, URL HTTP o archivo JSON |
| — | Alias para |
| — | Punto final SSE/HTTP remoto — implica |
| auto | Forzar transporte al destino: |
| 30 | Tiempo de espera de conexión para destinos SSE (reintentos 3×) |
| stdio | Cómo sirve el proxy a tu agente |
| 8080 | Puerto de escucha del proxy en |
| off | Imprime conteos de tokens por petición |
| WARNING | DEBUG / INFO / WARNING / ERROR |
Agrégalo a Claude Desktop:
{
"mcpServers": {
"my-server-via-refract": {
"command": "/path/to/refract-proxy",
"args": [
"--target",
"npx @modelcontextprotocol/server-filesystem /path/to/folder",
"--verbose"
]
}
}
}Para un servidor MCP remoto (SSE):
{
"mcpServers": {
"remote-via-refract": {
"command": "/path/to/refract-proxy",
"args": ["--url", "https://my-mcp-server.com/sse"]
}
}
}En lugar de editar las entradas una por una (o ejecutar refract-install por servidor), refract-wrap-all reescribe todos los servidores stdio en claude_desktop_config.json para que pasen por refract-proxy en un solo comando:
# Preview what would change — writes nothing
refract-wrap-all --dry-run
# Wrap every stdio server not already going through refract
refract-wrap-all
# Restore the original commands
refract-wrap-all --unwrapEjemplo: esta entrada
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["@modelcontextprotocol/server-filesystem", "/tmp"],
"env": {"MY_VAR": "1"}
}
}
}se convierte en
{
"mcpServers": {
"filesystem": {
"command": "/path/to/refract-proxy",
"args": ["--stdio-cmd", "npx @modelcontextprotocol/server-filesystem /tmp"],
"env": {"MY_VAR": "1"}
}
}
}Garantías:
Se hace una copia de seguridad de la configuración antes de cada escritura (claude_desktop_config.json.bak, luego .bak2, .bak3… — nunca se sobrescribe una copia existente).
env, cwd y cualquier otro campo del servidor se conservan.
Los servidores que ya pasan por refract-proxy o refract-server se saltan (already wrapped).
Los servidores remotos SSE/HTTP (entradas url) se saltan — solo se envuelven servidores stdio.
--unwrap es un viaje de ida y vuelta exacto: envolver y luego desenvolver restaura cada comando, argumentos y campos originales.
Flag | Valor | Descripción |
| Streamable HTTP | Estándar actual (especificación MCP 2025-03-26). Usar con servidores MCP remotos. |
| SSE | Transporte heredado, mantenido por compatibilidad. Usar si el servidor no soporta Streamable HTTP. |
| stdio subprocess | Comando local (defecto cuando |
(omitir) | detección automática | Inferido de |
Tanto sse como http requieren una URL HTTP(S) en --target.
# Connect to a remote MCP server via Streamable HTTP (recommended)
refract-proxy --target "https://my-mcp-server.com/mcp" --transport http
# Connect via SSE (legacy)
refract-proxy --target "https://my-mcp-server.com/sse" --transport sse
# Local subprocess (auto-detected, --transport stdio optional)
refract-proxy --target "npx @modelcontextprotocol/server-filesystem /tmp"Expone tu base de código como un servidor MCP. Tu agente puede indexar un repositorio, obtener contexto comprimido de archivos, expandir funciones específicas, analizar impacto, detectar cambios disruptivos y mapear riesgos de seguridad.
refract-server --root /path/to/your/repoAgrégalo a Claude Desktop:
{
"mcpServers": {
"refract-code": {
"command": "/path/to/refract-server",
"args": ["--root", "/path/to/your/repo"]
}
}
}Imagina una biblioteca con 50 libros.
Sin Refract: tu agente recibe un resumen detallado de los 50 libros en cada pregunta, incluso si la respuesta solo necesita uno de ellos.
Con Refract: tu agente primero recibe una lista de títulos (el índice). Una vez que sabe qué libro necesita, solo recibe el contenido de ese libro.
Técnicamente:
El índice (siempre enviado): solo los nombres de las herramientas y una breve descripción de cada una.
El detalle (enviado solo cuando es necesario): la descripción completa de la herramienta realmente utilizada, todo lo necesario para usarla correctamente, nada más.
La verificación: después de cada compresión, Refract comprueba automáticamente que no se haya eliminado nada importante. Si hay alguna duda, envía la versión completa en lugar de arriesgarse.
Ningún modelo de IA está involucrado en este proceso. Es completamente automático, rápido y determinista.
Herramienta | Qué hace |
Compresión | Comprime los esquemas de las herramientas sobre la marcha, hasta un 98% de reducción |
Verificación de señal | Verifica el contrato invocable después de cada compresión |
Enrutamiento semántico | Identifica la herramienta correcta usando embeddings (optativo) |
Caché de prompts | Inyecta cache_control de Anthropic para peticiones repetidas |
Herramienta | Entrada | Salida |
index_repo | ruta del repo | índice agregado de todos los archivos Python, JS, TS |
get_compressed | ruta del archivo | estructura comprimida + estadísticas de tokens |
expand | ruta del archivo + nombres de funciones | fuente textual + contexto de dependencias |
blast_radius | ruta del archivo + nombre de función | todas las funciones que se rompen si el objetivo cambia |
semantic_diff | ruta del archivo + fuente antigua + fuente nueva | cambios disruptivos vs cambios solo de cuerpo |
semantic_diff_branches | ruta del repo + archivo + función + referencias git base/head | semantic_diff de una función entre dos ramas/commits |
security_surface | ruta del repo | mapa de llamadas peligrosas (subprocess, eval, pickle, requests) |
refract-status --root /path/to/repo
refract-status --root /path/to/repo --jsonFlag | Descripción |
| Ruta a analizar (defecto: directorio actual) |
| Salida legible por máquina |
Muestra: archivos por lenguaje, tokens brutos vs comprimidos, funciones/clases indexadas, llamadas peligrosas por categoría, lenguajes sin soporte de tree-sitter.
Pide a Claude qué funciones se rompen si cambias una función objetivo.
Ejemplo de resultado:
{
"target": "authenticate",
"direct_callers": ["login_user"],
"all_impacted": ["login_user", "verify_session", "admin_access"],
"impacted_count": 3,
"risk_level": "MEDIUM"
}Niveles de riesgo: BAJO (de 0 a 2 afectadas), MEDIO (de 3 a 5), ALTO (6 o más).
Detecta cambios disruptivos en la API comparando interfaces de funciones, no cuerpos. Úsalo como puerta de CI.
Ejemplo de resultado:
{
"breaking": ["authenticate"],
"body_only": ["logout"],
"added": ["new_function"],
"removed": [],
"unchanged": ["hash_password"],
"is_breaking": true
}Si is_breaking es true, el PR cambia la API pública y debe ser revisado.
Mapa cada función que llama a primitivas peligrosas en todo tu repositorio.
RIESGO ALTO: subprocess, os.system, eval, exec, pickle, ctypes
RIESGO MEDIO: open (modo escritura), socket, requests, httpx, urllib
Ejemplo de resultado:
{
"high_risk": [
{
"file": "src/llm_client.py",
"function": "run_command",
"calls": ["subprocess.run"]
}
],
"summary": {
"high_risk_count": 1,
"medium_risk_count": 3,
"total_functions_scanned": 87,
"clean_files": 8
}
}Python (mediante módulo ast), JavaScript, TypeScript, JSX, TSX (mediante tree-sitter, optativo con pip install refract-mcp[multilang]).
El lenguaje se detecta automáticamente de la extensión del archivo. Caída gaci si tree-sitter no est instalado.
Refact se integra con el cché de prompts de Anthropic. as_anthropic_tols() marca automáticamente el catálogo comprimido como caable, reduciendo aú más ls costos en petiones repetidas.
Ejemplo en 30 días, 100 petiones al día, 5000 tokens de esquemas:
Escenario | Coste |
Sin Refract, sin caché | $45.00 |
Con Refract + caché | $1.49 |
"Failed to spawn process: No such file or directory" en Claude Desktop
Claude Desktop no encuentra refract-proxy en su PATH. Encuentra la ruta absoluta y úsala directamente:
which refract-proxyLuego usa la ruta completa en claude_desktop_config.json:
{
"mcpServers": {
"my-tool-via-refract": {
"command": "/full/path/to/refract-proxy",
"args": [
"--target",
"npx @modelcontextprotocol/server-filesystem /path/to/folder"
]
}
}
}Claude Desktop, Cursor, cualquier cliente que siga el estándar MCP, cualquier servidor MCP existente.
MIT — libre de usar, incluso comercialmente.
Reverse-call-graph impact analysis for a Python function: BFS over inverted call edges to find every function transitively affected by changing target_function. Returns direct_callers, all_impacted, impacted_count, total_functions and a risk_level. Python files only.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to a .py file (relative to --root or absolute). | |
| target_function | Yes | Function/method name to analyze the blast radius of. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavior: BFS algorithm, inverted call edges, returns specific fields (direct_callers, all_impacted, etc.), and scope (Python files only). No hidden side effects or destructive actions are implied.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loads the purpose, and includes all essential information without verbosity. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations or output schema, the description covers purpose, algorithm, input parameters, return fields, and file type restriction. It is complete for an agent to understand and use this tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (both params described), so baseline is 3. The description adds value by explaining the algorithm context (BFS over inverted call edges) and linking the parameters to the analysis process, though the schema already defines them clearly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Reverse-call-graph impact analysis for a Python function', specifying the verb (analyze impact), resource (Python function), and methodology (BFS over inverted call edges). It distinguishes from sibling tools like index_repo and security_surface which have different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly defines usage: when you need to know which functions are affected by changing a target function in a Python file. It does not explicitly compare with siblings, but the context is clear. The restriction 'Python files only' provides a clear constraint, earning a 4.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Given function/class names in a .py file, return them verbatim (full source) plus their compressed dependency context.
| Name | Required | Description | Default |
|---|---|---|---|
| targets | Yes | Function/class names to expand. | |
| file_path | Yes | Path to a .py file (relative to --root or absolute). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so description carries full burden. It states it returns 'full source' and 'compressed dependency context', which is a key behavioral trait. However, it does not disclose read-only nature, auth requirements, or potential performance implications (e.g., large files). Adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with purpose. No wasted words; all information is necessary and directly conveys the tool's action and output.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that there is no output schema and no annotations, the description is somewhat vague about the exact format of 'compressed dependency context'. While the tool is simple, the description could be more complete by clarifying what 'compressed' means. Sufficient but leaves room for ambiguity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters adequately. The tool description adds no new meaning beyond restating the schema descriptions, meeting the baseline but not adding value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description uses specific verb 'expand' on function/class names in a .py file, clearly indicating it returns full source plus dependency context. Differentiates from siblings like 'get_compressed' (which likely returns compressed content) and 'blast_radius' (impact analysis).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives like 'get_compressed' or 'blast_radius'. Usage is implied by the description (to get full source of specific definitions with dependencies), but lacks when-not-to-use or prerequisite information.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
S5-compress a single source file — Python or JS/TS (signatures + dependency contracts, bodies stripped) — and return the compressed structure plus token stats (tokens_before, tokens_after, reduction_pct).
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to a .py file (relative to --root or absolute). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must disclose behaviors. It does not state whether the operation is read-only or modifies files, nor does it mention side effects, auth requirements, or rate limits. The word 'compress' might imply mutation, but the return of a 'compressed structure' suggests the original file is unchanged. This ambiguity is a gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single well-structured sentence. It front-loads the action ('S5-compress a single source file'), specifies file types, details the compression behavior, and lists the output. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Without output schema, the description should explain the return value structure, but it does mention 'compressed structure plus token stats (tokens_before, tokens_after, reduction_pct),' which is helpful. However, it lacks behavioral context (read/write), does not resolve the file type inconsistency, and does not address how this relates to sibling tools like 'expand.' The minimal viable information is present, but gaps reduce completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (one parameter with description). The description adds that the tool supports Python and JS/TS, but the schema's parameter description says 'Path to a .py file,' which contradicts the broader file types stated in the tool description. This inconsistency misleads the agent and detracts from the value added beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool compresses a single source file (Python or JS/TS) by stripping bodies while keeping signatures and dependency contracts, and returns token stats. The verb 'compress' and resource 'source file' are specific, and it distinguishes from siblings like 'blast_radius' or 'expand' implicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. The description does not mention when to choose compression over expansion or other sibling tools, leaving the agent without decision context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Walk a repo (Python + JavaScript/TypeScript) and return an aggregated structural index: every function, class, import and dependency. Max depth 3; skips pycache, .git, venv, node_modules.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Repo path (relative to --root or absolute). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses maximum depth 3 and skipped directories (__pycache__, .git, venv, node_modules), but fails to mention behavior for unsupported file types, invalid paths, or performance implications for large repos. Additional context would improve transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences with front-loaded purpose and clear constraints. Every word adds value, no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description partially explains return value as 'aggregated structural index' listing functions, classes, imports, dependencies. However, it lacks details on output format (e.g., JSON structure, list vs. dict) and does not address edge cases like empty repos or mixed languages. It is acceptable but not fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a single required 'path' parameter described adequately. The description adds no extra parameter details beyond the schema, so baseline 3 is appropriate. The description's main value is in explaining the tool's overall function, not parameter specifics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool walks a repo and returns a structural index of functions, classes, imports, and dependencies, explicitly specifying supported languages (Python and JavaScript/TypeScript). This distinguishes it from sibling tools like 'blast_radius' or 'security_surface', which likely have different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide explicit guidance on when to use this tool versus alternatives like 'blast_radius' or 'expand'. It only implies usage for structural indexing, but lacks when-to-use, when-not-to-use, or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Walk a Python repo and find functions that call dangerous primitives — pure AST analysis, zero LLM calls. Classifies calls as HIGH risk (subprocess/os.system/eval/exec/pickle/import/ctypes …) or MEDIUM risk (sockets/requests/httpx/urllib/paramiko/smtplib and write-mode open()). Also scans for potential secrets: hardcoded keys/tokens (AKIA…, sk-…, ghp_…, token=/password=/api_key= assignments), .env/environment loading, and high-entropy token-looking literals. Returns high_risk, medium_risk, secrets, clean files and a summary. Max depth 3; skips pycache, .git, venv, node_modules.
| Name | Required | Description | Default |
|---|---|---|---|
| repo_path | Yes | Repo path (relative to --root or absolute). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It clearly states pure AST analysis, zero LLM calls, risk classification levels, secret detection, max depth 3, and skipped directories. Could mention whether the tool is read-only (likely yes) but overall quite transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is front-loaded with the main action and packed with relevant details in three sentences. Minimal redundancy, though length could be trimmed slightly without losing meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, description adequately explains return values (high_risk, medium_risk, secrets, clean files, summary). Covers key behaviors and limitations. Could mention file type filtering but sufficient for an agent to understand scope.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter (repo_path) with 100% schema coverage. Description adds no extra detail beyond the schema's description of the path. Baseline score is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it walks a Python repo using AST analysis to find dangerous function calls and secrets, with specific risk classifications. No sibling tool overlaps, making its unique purpose unmistakable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use (security scanning of Python repos) but does not explicitly state when not to use or mention alternatives among siblings. More precise guidance would improve this dimension.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.7.0blast_radiusexpandget_compressedindex_reposecurity_surfaceScored across 5 tools
Each tool has a distinct purpose: impact analysis, source retrieval, file compression, repo indexing, and security scanning. No two tools overlap in functionality.
All tools use snake_case, but 'expand' is a lone verb while others follow a verb_noun pattern (e.g., get_compressed, index_repo). Minor inconsistency but still clear.
5 tools is a well-scoped set for a static analysis toolkit. Neither too few nor too many, each tool serves a clear need.
Covers core static analysis needs (impact, source, compression, indexing, security). Missing a dedicated diff or test analysis tool, but the surface is reasonably complete for the domain.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
