Anyreach
Server Details
Build AI agents that handle calls, web chats, and email — and automate everything around them.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 7 tools
The four call_* tools split by risk class (read / create / change / live) rather than by resource, which is non-obvious at first glance (e.g. creating a phone number is 'live' but creating an agent is 'create'). However, the descriptions are explicit about each bucket's scope and every operation carries a `call_with` field from search_tools/describe_tool, with misroutes refused, so ambiguity is resolvable rather than fatal. list_all_tools and search_tools overlap slightly as discovery paths but serve distinct lookup styles.
All seven tools are snake_case and follow a verb_noun(_tool) pattern: call_read_tool, call_create_tool, call_change_tool, call_live_tool, list_all_tools, describe_tool, search_tools. The three discovery tools use the same verb_noun convention as the invocation tools.
Seven tools is well within the sweet spot, and the small surface is intentional: a thin meta-layer (list/describe/search + 4 dispatching call tools) fronting a much larger upstream operation catalog. Each tool earns its place.
The four call buckets cover the full lifecycle — read, create, edit/delete, and live/external side effects — and discovery is covered by list, search, and schema lookup. Minor gap: there is no tool to list the user's organizations, so multi-org disambiguation relies on a refusal message that returns the org list.
Publisher details
- Operator
- Anyreach, Inc.
- Operator website
- https://anyreach.ai
- Vendor relationship
- Not applicable
- Documentation
- https://docs.anyreach.ai/mcp/connecting-a-client
- Privacy policy
- Not provided
- Trust center
- https://anyreach.trust.site/
- Restrictions
- Not applicable
Available Tools
7 toolscall_change_toolRun a change or delete operationADestructiveInspect
Invoke an Anyreach operation that edits or deletes existing configuration or data — agents, knowledge bases, widgets, labels, credentials, custom tables, campaign settings. Each operation's risk and call_with (from search_tools or describe_tool) name the one call tool that runs it; the others refuse it. organization_id is the Anyreach organization to act on behalf of — most operations are organization-scoped. You may omit it: if the user belongs to exactly one organization it is used automatically, and if they belong to several the call is refused with the list, so ask which one and retry. arguments must conform to the operation's inputSchema. Returns the upstream JSON response.
Inputs: name (required), arguments, organization_id.
call_create_toolRun a create operationAInspect
Invoke an Anyreach operation that adds something new — an agent, a draft version, a knowledge base or source, a widget, a workflow — without overwriting or removing anything that exists. Each operation's risk and call_with (from search_tools or describe_tool) name the one call tool that runs it; the others refuse it. organization_id is the Anyreach organization to act on behalf of — most operations are organization-scoped. You may omit it: if the user belongs to exactly one organization it is used automatically, and if they belong to several the call is refused with the list, so ask which one and retry. arguments must conform to the operation's inputSchema. Returns the upstream JSON response.
Inputs: name (required), arguments, organization_id.
call_live_toolRun a live operationADestructiveInspect
Invoke an Anyreach operation that affects live traffic or the world outside the platform: publishing or deploying, dialling or messaging people, editing campaigns or adding their contacts, starting experiments, running workflows or creating their triggers, phone numbers, email addresses, trunks and inbound routing, greeting audio, credential secrets, and removing an unsubscribe. Each operation's risk and call_with (from search_tools or describe_tool) name the one call tool that runs it; the others refuse it. organization_id is the Anyreach organization to act on behalf of — most operations are organization-scoped. You may omit it: if the user belongs to exactly one organization it is used automatically, and if they belong to several the call is refused with the list, so ask which one and retry. arguments must conform to the operation's inputSchema. Returns the upstream JSON response.
Inputs: name (required), arguments, organization_id.
call_read_toolRun a read operationARead-onlyInspect
Invoke an Anyreach operation that only reads: lists, details, transcripts, metrics, searches and previews. Changes nothing. Each operation's risk and call_with (from search_tools or describe_tool) name the one call tool that runs it; the others refuse it. organization_id is the Anyreach organization to act on behalf of — most operations are organization-scoped. You may omit it: if the user belongs to exactly one organization it is used automatically, and if they belong to several the call is refused with the list, so ask which one and retry. arguments must conform to the operation's inputSchema. Returns the upstream JSON response.
Inputs: name (required), arguments, organization_id.
describe_toolDescribe an Anyreach operationARead-onlyInspect
Fetch the JSON Schema and metadata for a single tool by name. Use this after list_all_tools when you've picked a tool and need its input schema before calling it.
Inputs: name (required). Returns: result
list_all_toolsList Anyreach operationsARead-onlyInspect
List every tool exposed by this MCP server with a one-line description. Returns names + descriptions only — call describe_tool(name) to get the input schema for a specific tool, or search_tools(query) to find tools by topic.
Inputs: no named parameters. Returns: result
search_toolsSearch Anyreach operationsARead-onlyInspect
Find tools relevant to a natural-language query. Returns the top matches with their input schemas inline, ready to invoke via the call tool named in each match's call_with.
Inputs: query (required), limit. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceRemote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.MIT
- AlicenseCqualityCmaintenanceCompetitor Monitor AI - MCP server providing AI-powered tools and automation by MEOK AI Labs112 npm46 PyPIMIT
- AlicenseAqualityDmaintenanceEnables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.1611 npm1MIT

industrylens-mcpofficial
AlicenseNot gradedqualityCmaintenanceBrowse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.