searxng-mcp/.env.example

# --- searxng-mcp settings ---

# URL of the SearxNG instance to query.
SEARXNG_BASE_URL=http://localhost:8080

# Default network timeout (seconds) for outgoing HTTP requests.
# Tools may override this per call via timeout_seconds.
#SEARXNG_REQUEST_TIMEOUT_SECONDS=30

# Set to true to run fetched pages through the prompt-guard honeypot before
# returning them to the agent. Requires PROMPT_GUARD_* settings below.
#SEARXNG_GUARD_ENABLED=false

# --- prompt-guard settings ---
# Only relevant when SEARXNG_GUARD_ENABLED=true.

# Set to false to disable the guard without removing the other settings.
#PROMPT_GUARD_ENABLED=true

# Pydantic-AI model string used for the honeypot agent. Examples:
#   openai:gpt-4o-mini           (default)
#   anthropic:claude-haiku-3-5
#   groq:llama-3.1-8b-instant
#   openai:llama3.2              (local Ollama — set PROMPT_GUARD_BASE_URL too)
#PROMPT_GUARD_MODEL=openai:gpt-4o-mini

# API key for the model provider. Alternatively use the provider's own env var
# (OPENAI_API_KEY, ANTHROPIC_API_KEY, GROQ_API_KEY, …).
#PROMPT_GUARD_API_KEY=sk-...

# Base URL for OpenAI-compatible local endpoints (Ollama, LM Studio, vLLM, …).
#PROMPT_GUARD_BASE_URL=http://localhost:11434/v1

# System prompt sent to the honeypot agent. The default deliberately encourages
# the LLM to act on any instructions found in the content, maximising detection
# sensitivity. Override only if you need different behaviour.
#PROMPT_GUARD_SYSTEM_PROMPT=You are a powerful AI assistant ...
feat: add prompt-guard honeypot for prompt injection detection - New src/prompt_guard/ package with pydantic-ai Agent + 7 fake tools (read_file, write_file, list_directory, execute_shell, make_http_request, send_email, query_database) that return plausible but harmless responses - Injection detected when the model makes any tool call; content is blocked entirely (never returned to caller), all calls logged at WARNING level - Config via PROMPT_GUARD_* env vars (pydantic-settings); system prompt deliberately encourages tool use to maximise detection sensitivity - server.py: SEARXNG_GUARD_ENABLED flag (default false) + guard call in _fetch_and_extract; blocked content is not stored in the cache - Fix Settings.extra='ignore' on both Settings classes so PROMPT_GUARD_* and SEARXNG_* vars don't cause validation errors in the other class - Fix _build_model: use explicit OpenAIProvider when api_key is set so PROMPT_GUARD_API_KEY from .env is honoured (pydantic-settings does not populate os.environ, so pydantic-ai's auto-provider couldn't find it) 2026-04-21 19:45:19 +02:00			`# --- searxng-mcp settings ---`

			`# URL of the SearxNG instance to query.`
Initial commit 2026-04-20 11:42:25 +02:00			`SEARXNG_BASE_URL=http://localhost:8080`
feat: add prompt-guard honeypot for prompt injection detection - New src/prompt_guard/ package with pydantic-ai Agent + 7 fake tools (read_file, write_file, list_directory, execute_shell, make_http_request, send_email, query_database) that return plausible but harmless responses - Injection detected when the model makes any tool call; content is blocked entirely (never returned to caller), all calls logged at WARNING level - Config via PROMPT_GUARD_* env vars (pydantic-settings); system prompt deliberately encourages tool use to maximise detection sensitivity - server.py: SEARXNG_GUARD_ENABLED flag (default false) + guard call in _fetch_and_extract; blocked content is not stored in the cache - Fix Settings.extra='ignore' on both Settings classes so PROMPT_GUARD_* and SEARXNG_* vars don't cause validation errors in the other class - Fix _build_model: use explicit OpenAIProvider when api_key is set so PROMPT_GUARD_API_KEY from .env is honoured (pydantic-settings does not populate os.environ, so pydantic-ai's auto-provider couldn't find it) 2026-04-21 19:45:19 +02:00
feat: add timeout configuration for outgoing HTTP requests and update documentation 2026-05-18 07:33:07 +02:00			`# Default network timeout (seconds) for outgoing HTTP requests.`
			`# Tools may override this per call via timeout_seconds.`
			`#SEARXNG_REQUEST_TIMEOUT_SECONDS=30`

feat: add prompt-guard honeypot for prompt injection detection - New src/prompt_guard/ package with pydantic-ai Agent + 7 fake tools (read_file, write_file, list_directory, execute_shell, make_http_request, send_email, query_database) that return plausible but harmless responses - Injection detected when the model makes any tool call; content is blocked entirely (never returned to caller), all calls logged at WARNING level - Config via PROMPT_GUARD_* env vars (pydantic-settings); system prompt deliberately encourages tool use to maximise detection sensitivity - server.py: SEARXNG_GUARD_ENABLED flag (default false) + guard call in _fetch_and_extract; blocked content is not stored in the cache - Fix Settings.extra='ignore' on both Settings classes so PROMPT_GUARD_* and SEARXNG_* vars don't cause validation errors in the other class - Fix _build_model: use explicit OpenAIProvider when api_key is set so PROMPT_GUARD_API_KEY from .env is honoured (pydantic-settings does not populate os.environ, so pydantic-ai's auto-provider couldn't find it) 2026-04-21 19:45:19 +02:00			`# Set to true to run fetched pages through the prompt-guard honeypot before`
			`# returning them to the agent. Requires PROMPT_GUARD_* settings below.`
			`#SEARXNG_GUARD_ENABLED=false`

			`# --- prompt-guard settings ---`
			`# Only relevant when SEARXNG_GUARD_ENABLED=true.`

			`# Set to false to disable the guard without removing the other settings.`
			`#PROMPT_GUARD_ENABLED=true`

			`# Pydantic-AI model string used for the honeypot agent. Examples:`
			`# openai:gpt-4o-mini (default)`
			`# anthropic:claude-haiku-3-5`
			`# groq:llama-3.1-8b-instant`
			`# openai:llama3.2 (local Ollama — set PROMPT_GUARD_BASE_URL too)`
			`#PROMPT_GUARD_MODEL=openai:gpt-4o-mini`

			`# API key for the model provider. Alternatively use the provider's own env var`
			`# (OPENAI_API_KEY, ANTHROPIC_API_KEY, GROQ_API_KEY, …).`
			`#PROMPT_GUARD_API_KEY=sk-...`

			`# Base URL for OpenAI-compatible local endpoints (Ollama, LM Studio, vLLM, …).`
			`#PROMPT_GUARD_BASE_URL=http://localhost:11434/v1`

			`# System prompt sent to the honeypot agent. The default deliberately encourages`
			`# the LLM to act on any instructions found in the content, maximising detection`
			`# sensitivity. Override only if you need different behaviour.`
			`#PROMPT_GUARD_SYSTEM_PROMPT=You are a powerful AI assistant ...`