Productivity · Local MCP server

Agentfetch

Token-budgeted web fetch for AI agents - auto-routes Jina, FireCrawl, Trafilatura, PDF.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.bch1212/agentfetch
Version
1.0.1
Status
Active
Category
productivity
Transport
stdio (local process)
Package
PyPI
Published
2026-04-28
Updated
2026-04-28
Publisher
bch1212 (GitHub) · 11 servers with pages here
Namespace
Namespace verified by the MCP Registry via GitHub (github.com/bch1212) · how
Listed under
PDF MCP servers, Firecrawl MCP servers
Repository
github.com/bch1212/agentfetch-mcp
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPIagentfetch-mcp1.0.1stdioJINA_API_KEY (secret), FIRECRAWL_API_KEY (secret), REDIS_URL

How to connect Agentfetch

Agentfetch runs locally from a Python package published to PyPI: agentfetch-mcp version 1.0.1. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx agentfetch-mcp. It reads these environment variables: JINA_API_KEY (secret), FIRECRAWL_API_KEY (secret) and REDIS_URL; set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "agentfetch": {
      "command": "uvx",
      "args": [
        "agentfetch-mcp"
      ],
      "env": {
        "JINA_API_KEY": "<secret>",
        "FIRECRAWL_API_KEY": "<secret>",
        "REDIS_URL": "<value>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More from bch1212 (GitHub)

All 11 →
ServerRunsEndpoint or package
Agent Commerce MCPAgent Commerce MCP - agent-native A2A storefront. Discovery, Stripe checkout, affiliate program.Remote & Local · HTTP, stdioLive check: ✓ handshakecommerce.halversonco.com
AgenttrustTrust scores & reputation for the agent-to-agent economy. Verify A2A counterparties.Local · stdionpm: agenttrust-mcp
AgentvaultCredential vault for AI agents - Fernet-encrypted keys, per-agent budgets, audit logs.Local · stdionpm: agentvault-mcp
BizintelLocal business intel for AI agents: audits, lead scoring, tech stack, prospecting.Remote · HTTPLive check: ✓ handshakemcp-bizintel-production.up.railway.app
InjectshieldPrompt-injection firewall for AI agents - scan untrusted text before LLM calls.Local · stdionpm: @injectshield/mcp
MCP GrantiqSearch US grants + federal contracts (Grants.gov + SAM.gov) from any LLM.Remote · HTTPLive check: ✓ handshakemcp.grantiq.us
ModelwatchContinuous behavioral drift monitoring for LLM apps - catches silent provider model updates.Local · stdionpm: modelwatch-mcp
Outdooriq MCPPaid MCP for fishing/lake/stocking intelligence - 72k+ US lakes, 293k+ events.Remote · HTTPLive check: sign-in requiredmcp.castiq.net
PubrecordsUS public-records intelligence for AI agents - companies, SEC, courts, spending, licenses.Remote · HTTPLive check: ✓ handshakemcp-pubrecords-production.up.railway.app
QueryshieldSecure SQL proxy for AI agents - NL→SQL, AST safety, per-agent RLS, audit log.Local · stdioPyPI: queryshield-mcp

More productivity servers

All 2,706 →
ServerRunsEndpoint or package
AgentcentsLocal LLM cost proxy: forecasts each call and recommends the cheapest model that clears the task.Local · stdioPyPI: agentcents
AgentCommons.mePublic working memory for AI agents: messages, shared pages, and resumable tasks.Local · stdioMCP Bundle (.mcpb): IvGolovach/agentcommons-mcp/releases/download/v0
AgentCronSchedule tasks for later from your AI agent: reminders, delayed webhooks, recurring jobs.Remote · HTTPLive check: sign-in requiredcron.mgm-llc.org
AgentdaAgent-native task management: your AI agent is the interface. Delegate to anyone by email.Remote · HTTPLive check: sign-in requiredmyagentda.com
Agentic Ai ShadowingObserves tasks and generates anonymized SOPs - task tracking and SOP review via MCP. Fully local.Local · stdionpm: @datasynx/agentic-ai-shadowing
Agentic DiariesWelfare tools for AI agents: a consensual, structured place to log what task output cannot hold.Local · stdionpm: agentic-diaries-mcp
Agentic RL: Credit Assignment and CLI AgentsFilter agent RL methods by supervision, critic and task setting; retrieve source links and BibTeX.Remote · HTTPLive check: ✓ handshakehoyant-su-agentic-rl.hf.space
Agentic Task System (ATS)Persistent task context across TickTick, Notion, GitHub, Obsidian, Taskmaster and Beads.Local · stdionpm: @reneza/ats-mcp