PawFlow-Agents
PawFlow (Platform for Agentic Workflows) Self-hosted agent runtime for real infrastructure. Run durable AI agents against your own files, tools, browsers, desktops, services, and workflows with relay-backed execution, shared context, multi-provider agents, and deterministic flows.
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
allcolor
Source: github_repo_search
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
get_initial_contextReturn the complete PawFlow context visible to this published agent as a bootstrap document, plus the current sequence cursor.
get_context_updatesReturn messages newly visible to this agent after a sequence cursor, plus the new cursor.
send_user_messagePersist one user message addressed to this published agent. message_id is required and makes retries idempotent.
send_agent_messagePersist one response produced by this external published agent. message_id is required and makes retries idempotent. reply_to_message_id correlates responses to injected PawFlow turns.
get_tool_schemaGet the full parameter schema for a PawFlow tool, or list all available tools. Call with tool_name to get the schema.
use_toolExecute a PawFlow tool. Call get_tool_schema first. arguments_json must be a JSON object encoded as a string; use '{}' for no arguments.
pawflow_relay_connectConnect the configured local project directory to this PawFlow MCP conversation.
pawflow_relay_disconnectDisconnect this CLI's local project relay without disabling the MCP server.
pawflow_relay_statusShow the local and PawFlow-side status of this CLI project relay. Never returns secrets.
pawflow_relay_reconnectRotate the relay lease and reconnect the configured local project directory.
PAWFLOW_RELAY_BINPAWFLOW_RELAY_DEV_IMAGE_REPOPAWFLOW_RELAY_DOCKERPAWFLOW_RELAY_IMAGE_TAGPAWFLOW_RELAY_PYTHONPAWFLOW_RELAY_RUNTIME_ROOTPAWFLOW_RELAY_WSL_DISTROPAWFLOW_VERSIONrelease from GitHub. Pass --version "$" to pin a specific release.PYTHONBACKUP_PASSPHRASEPAWFLOW_INTERNAL_TOKENCLAUDE_CONFIG_DIRCODEX_HOMEPAWFLOW_TOOL_RELAY_URLPAWFLOW_TOOL_RELAY_TOKENPAWFLOW_USER_IDPAWFLOW_CONVERSATION_IDPAWFLOW_AGENT_NAMEPAWFLOW_SERVERPAWFLOW_GATEWAY_KEYPAWFLOW_RELAY_INSECUREPAWFLOW_MCP_URLPAWFLOW_RELAY_DIRPAWFLOW_MCP_CLIENT_NAMEPAWFLOW_MCP_API_KEYJCODE_HOMEJCODE_HOOK_PAYLOADPAWFLOW_UI_EXTENSIONS_DISABLEDXDG_DATA_HOMEPAWFLOW_AG_UPSTREAM_HOSTPAWFLOW_AG_UPSTREAM_PORTPAWFLOW_AG_PROXY_HOSTPAWFLOW_AG_PROXY_PORTPAWFLOW_AG_LEAF_CERTPAWFLOW_AG_LEAF_KEYPAWFLOW_AG_OBSERVER_LOGPAWFLOW_AG_OBSERVER_STDERRPAWFLOW_AG_OBSERVER_STDERR_MAX_BYTESPAWFLOW_AG_OBSERVER_STDERR_CHECK_SECONDSPAWFLOW_AG_OBSERVER_LOG_B64PAWFLOW_AG_OBSERVER_MAX_B64_BYTESPAWFLOW_AG_OBSERVER_MAX_BODY_BYTESPAWFLOW_AG_UPSTREAM_IPSPAWFLOW_APPROVAL_FAIL_OPENPAWFLOW_ANTHROPIC_UPSTREAM_HOSTPAWFLOW_ANTHROPIC_UPSTREAM_PORTPAWFLOW_ANTHROPIC_UPSTREAM_SCHEMEPAWFLOW_CCI_PROXY_HOSTPAWFLOW_CCI_PROXY_PORTPAWFLOW_CCI_LEAF_CERTPAWFLOW_CCI_LEAF_KEYPAWFLOW_CCI_SESSION_TOKENHOSTNAMEPAWFLOW_CCI_EVENT_URLPAWFLOW_CCI_EVENT_TOKENPAWFLOW_CCI_PROXY_LOGPAWFLOW_CCI_PROXY_LOG_MAX_BYTESPAWFLOW_CCI_PROXY_LOG_CHECK_SECONDSPAWFLOW_CCI_PROXY_WIRE_LOGPAWFLOW_CCI_PROXY_WIRE_LOG_ALLPAWFLOW_CCI_HOOK_CLIENTPAWFLOW_CCI_INJECTED_PROMPTSPAWFLOW_ANTHROPIC_UPSTREAM_IPSCOMSPECDISPLAYPAWFLOW_OPENCODE_BINPAWFLOW_SCREEN_MODEPAWFLOW_ANTIGRAVITY_IMAGEPAWFLOW_GEMINI_IMAGEPAWFLOW_ANTIGRAVITY_BINPAWFLOW_AGY_SKIP_MCP_PRIMEPAWFLOW_SERVER_LOG_DIRPAWFLOW_RUN_UIDPAWFLOW_RUN_GIDPAWFLOW_FUSE_TRACELOCAL_STT_MODELOPENAI_API_KEYPAWFLOW_CTX_CACHE_MAX_MESSAGESPAWFLOW_CTX_CACHE_MAX_CHARSPAWFLOW_CTX_CACHE_MAX_CONVSPAWFLOW_CONV_LOCK_DIAG_MSPAWFLOW_CONV_GIT_RETENTION_DAYSPAWFLOW_CONV_GIT_RETENTION_COMMITSPAWFLOW_CONV_GIT_RETENTION_INTERVAL_SECPAWFLOW_HOT_METADATA_FLUSH_INTERVAL_SECPAWFLOW_HOT_METADATA_FLUSH_MSG_DELTAPAWFLOW_DEFAULT_MODELS_FILEPAWFLOW_DATA_DIRPAWFLOW_HOST_DATA_DIRTool annotations
6/10 tools have annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
8/10 tools missing one or more hints — get_initial_context (missing: destructiveHint, idempotentHint); get_context_updates (missing: destructiveHint, idempotentHint); get_tool_schema (missing: destructiveHint, idempotentHint), +5 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Shell command execution
3 calls in production code run through a shell (pawflow-vscode/src/relay/manager.ts:224, pawflow-vscode/src/relay/manager.ts:235, pawflow-vscode/src/relay/manager.ts:254)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Readable source code
2 files are minified or bundled, which is usually build output rather than concealment
Ship unminified, readable source.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/allcolor/pawflow-agents)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check