MeshFlow
  • Cloud PlatformDeployIntegrationsInit CLIWhy MeshFlow
  • DocsLearn
  • CustomersCertificationBlogChangelogCommunity
  • Pricing
Sign inGet started
Pricing
Sign inGet started
MeshFlow

The production-safe standard for agentic AI.
Apache 2.0 — free forever.

Product
  • Pricing
  • Cloud
  • Compare
  • Init CLI
  • Changelog
Docs
  • Quickstart
  • Core concepts
  • Compliance guide
  • Token optimization
  • API reference
Resources
  • Blog
  • Customers
  • Community
  • PyPI
  • GitHub
Company
  • Discord
  • Twitter
  • Security
  • License
MeshFlow © 2026 · Yaya Systems · Apache 2.0
All systems operational
MeshFlowdocs
Search docs...⌘K
v1.13.0 GitHub Discord
Getting startedQuickstartInstallationCore conceptsHarness architectureSkills vs ToolsSandbox mode
GuidesBuilding agentsMulti-agent workflowsModel RoutersCost AnalyticsCompliance guideToken optimization
Claude & AIAdvisor patternThinking budgetsDynamic workflowsContext compactionTool streaming
Governancemeshflow-forensicZero-Trust PoliciesSOC 2 assertionEU AI ActProduction Readiness
IntegrationsOpenAI Agents SDKLangGraphCrewAIMCP ToolsTypeScript SDKOTel / OTLPAutoGen 0.4+
API ReferenceWorkflowAgentCostCapAdvisorAgentCostRegressionGate
Docs/Integrations/MCP Tools

MCP Tools

MeshFlow can auto-trace any MCP server tool call. Every call emits a tool_call span with the tool name, input hash, output hash, and latency — no changes to the MCP server or tool definition.

Install

bash
pip install "meshflow[mcp]" # Python
npm install @meshflow/mcp-tracer # TypeScript

Auto-trace

Wrap your MCP client with TracedMcpClient. All tool calls are intercepted and forwarded to MeshFlow spans automatically.

python
from meshflow.adapters.mcp import TracedMcpClient

mcp = TracedMcpClient(
server_url="http://localhost:8000",
cloud=cloud,
run_id="run-abc123",
)
result = await mcp.call_tool("web_search", {"query": "AI governance 2025"})

Manual span

Emit a tool_call span directly from any tool wrapper.

python
cloud.ingest_span(
run_id="run-abc123", agent_name="my_agent",
span_type="tool_call", name="web_search",
input_text=query, output_text=result,
tool_version="web_search@1.2.0",
)

TypeScript

typescript
import { TracedMcpClient } from '@meshflow/mcp-tracer';

const mcp = new TracedMcpClient({ serverUrl, apiKey, runId });
const result = await mcp.callTool('web_search', { query });
Previous
CrewAI
Next
TypeScript SDK
On this pageInstallAuto-traceManual spanTypeScript