Enables AI clients to discover and execute company-scoped workflows and conditional API calls through a repository MCP adapter.
Also known as mishrasanjeev/agentic-org, agentic-org, agenticorg-mcp-server
- Stars
- 14
- Tools
- 16
- Downloads, 30 days
- —
- Latest version
- 5.0.0
- Last commit
- Nov 15, 2026
- License
- —
What is AgenticOrg MCP?
AgenticOrg enables AI clients to discover and execute company-scoped workflows and conditional API calls through a repository MCP adapter. It exposes 16 tools, such as list_agents, run_agent, get_agent_details.
Summary generated from the project's README
About AgenticOrg MCP server
AgenticOrg provides an enterprise platform for building and governing agent workflows across departments like finance, HR, and marketing. The MCP server acts as an adapter that allows AI clients to discover and execute company-scoped workflows and conditional API calls through a repository. It is designed for organizations requiring structured agentic-commerce and back-office automation, though individual personal use remains free under the Orchestrum Personal Use License 1.0.
Users can connect various communication channels including WhatsApp Cloud API, Telegram, Meta Messenger, and Mailgun email to their agents. The system supports bringing your own AI credentials, such as Google provider keys, and allows for specific model configurations like Gemini thinking profiles for multi-step reasoning. While the MCP server and SDKs are open source under Apache 2.0, organizations must sign a commercial agreement with Orchestrum Technologies LLP to use or evaluate the full platform.
What you can do with it
- 1Automate customer service channelsDevelopers can connect agents to messaging platforms like Telegram or WhatsApp to handle inbound communications.
- 2Implement governed business onboardingOrganizations can deploy workflows that include deterministic policy scoring and human review for onboarding new providers.
- 3Integrate multi-step reasoningUsers can configure agents to use medium reasoning profiles for complex tasks that require more thought.
Written from the project's README. Every use case is checked against a quote from it.
How to install AgenticOrg MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall AgenticOrg MCP in Claude Code
$ claude mcp add agentic-org -- npx -y agenticorg-mcp-serverInstall AgenticOrg MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agentic-org": {
"command": "npx",
"args": [
"-y",
"agenticorg-mcp-server"
]
}
}
}Install AgenticOrg MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agentic-org": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agenticorg-mcp-server"
]
}
}
}Install AgenticOrg MCP in VS Code CLI
$ code --add-mcp '{"name":"agentic-org","type":"stdio","command":"npx","args":["-y","agenticorg-mcp-server"]}'Install AgenticOrg MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"agentic-org": {
"command": "npx",
"args": [
"-y",
"agenticorg-mcp-server"
]
}
}
}Install AgenticOrg MCP in Codex
$ codex mcp add agentic-org -- npx -y agenticorg-mcp-serverInstall AgenticOrg MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.agentic-org] command = "npx" args = ["-y", "agenticorg-mcp-server"]
Install AgenticOrg MCP in Gemini CLI
$ gemini mcp add -s user agentic-org npx -- -y agenticorg-mcp-serverInstall AgenticOrg MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agentic-org": {
"command": "npx",
"args": [
"-y",
"agenticorg-mcp-server"
]
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for agenticorg-mcp-server 5.0.0 in an isolated container with no network and no keys. It answered and listed 16 tools.
AgenticOrg MCP tools 16
Read from the server with tools/listlist_agentsList agent records returned by the configured endpoint. Optionally filter by domain.
run_agentSubmit a tenant-authenticated, company-scoped request to the configured A2A endpoint.
get_agent_detailsGet the agent record returned by the configured endpoint.
create_agent_from_sopParse SOP text into a draft configuration that requires review.
deploy_agentSubmit a reviewed configuration as a company-scoped shadow candidate.
list_connectorsList connector records for discovery. Presence does not establish runtime configuration or execution authority.
list_mcp_toolsList agent-tool records returned by the configured MCP endpoint. Results are environment-specific.
discover_agents_a2aDiscover available agent skills via A2A (Agent-to-Agent) protocol. Returns agent capabilities, input schemas, and domains.
get_agent_cardGet the A2A Agent Card - the public discovery document describing this AgenticOrg instance's capabilities.
seller.list_productsList cached Seller Commerce Agent product snapshots with source and freshness metadata.
seller.search_productsSearch cached Seller Commerce Agent product snapshots. Results are not transaction authority.
seller.get_product_factsAnswer product fact questions from cached Shopify-backed OACP artifacts.
Show all 16 toolsShow fewer tools
seller.get_offer_snapshotReturn cached price/offer snapshot labels. It does not create price locks or checkout sessions.
seller.get_inventory_snapshotReturn cached inventory snapshot labels. Inventory is a snapshot, not a reservation.
seller.get_mandate_capabilityRead cached mandate/payment capability posture from OACP protocol adapter metadata. It does not create mandates, checkout sessions, orders, or payments.
seller.ask_product_questionAsk a buyer-safe product question from cached artifacts. Final commitments are refused.
Configuration
AGENTICORG_ENV
Automated checks
Ran Nov 13, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work · What to fix for more points
- Source repository linked and reachablePass
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHub[!IMPORTANT] Commercial agreement required. Any organisation (a company, firm, partnership, LLP, charity, school, university, research body or government body) must sign a commercial agreement with Orchestrum Technologies LLP before it uses, evaluates, tests, pilots, hosts or deploys the AgenticOrg platform. Use without a signed agreement is not licensed and infringes Orchestrum Technologies LLP's copyright; under section 5 of the LICENSE, rights under the licence terminate automatically. To request an agreement, write to sanjeev@orchestrum.in and see COMMERCIAL-LICENSE.md. An individual's own personal use of the platform is free. The SDKs (
sdk/,sdk-ts/) and the MCP server (mcp-server/) are open source under the Apache License 2.0.
AgenticOrg
AgenticOrg is an enterprise AI agent platform for building, running, and governing agent workflows across finance, HR, marketing, operations, back office, communications, and bounded agentic-commerce use cases. The platform is source-available under the Orchestrum Personal Use License 1.0: only individuals' personal use is free, and any organisation needs a signed agreement with Orchestrum Technologies LLP; the SDKs and MCP server are Apache-2.0 open source (see Licence).
Ownership: AgenticOrg is owned by Orchestrum Technologies LLP.
Inventor / Owner: Sanjeev Kumar
Contact: sanjeev@orchestrum.in | mishra.sanjeev@gmail.com
Website demo and trial lead notifications default to sanjeev@orchestrum.in.
Self-hosted operators can select their own single marketing inbox with
AGENTICORG_DEMO_NOTIFY_TO. This does not redirect requester confirmations,
workspace notifications, or account-recovery email, and does not replace SMTP setup.
See the canonical ownership and contact statement and NOTICE.
Website | Application | Playground | User manual | Technical documentation | Current product status | Security policy
Start with a measurable pilot: bank service cases, fintech/API integrations, or merchant and external-buyer workflows. The visual rollout checklist explains source setup, review, external confirmation and expansion. Discuss your task and systems at sanjeev@orchestrum.in; do not send credentials or customer data in a public enquiry.
Licence
The AgenticOrg platform is source-available under the Orchestrum Personal Use License 1.0. Only an individual using it for their own personal purposes is free. Every organisation (companies, firms, sole proprietors' businesses, charities, schools, universities, research bodies and government) needs prior written permission in a signed agreement with Orchestrum Technologies LLP, for any use: evaluation, testing, pilots, internal use, hosting, resale or embedding, paid or free.
The AgenticOrg SDKs (sdk/, sdk-ts/) and the MCP server (mcp-server/) are open source
under the Apache License 2.0, free for any use including commercial.
| Directory | Licence |
|---|---|
sdk/ (Python SDK) |
Apache License 2.0: open source, free for any use including commercial |
sdk-ts/ (TypeScript SDK) |
Apache License 2.0: open source, free for any use including commercial |
mcp-server/ (MCP server) |
Apache License 2.0: open source, free for any use including commercial |
tests/fixtures/ucp/, core/commerce/acp/schemas/ (vendored protocol schemas) |
Apache License 2.0 (third-party, unchanged) |
Everything else: the AgenticOrg platform (api/, core/, auth/, connectors/, ui/ and the website, workers, docs/, scripts/, migrations/, tests) |
Orchestrum Personal Use License 1.0: individuals' personal use only; any organisation needs a signed agreement with Orchestrum Technologies LLP |
- Free (platform): an individual's own personal use only. Distributing the platform needs a written agreement too.
- Commercial licence: see COMMERCIAL-LICENSE.md and write to sanjeev@orchestrum.in.
- Existing users: these terms apply to every version published on or after 21 October 2026, including all updates. Versions published before that date remain available under the Apache License 2.0 they were released with. Existing and new users alike need a signed agreement for any use by or for an organisation of a version from 21 October 2026 onward.
- Trademarks: "AgenticOrg" and "Grantex" are trademarks of Orchestrum Technologies LLP; commercial use of the names, logos, hosted services or brand needs prior written approval with any version. See TRADEMARKS.md.
Source of truth
Live product totals and the deployed product version are published by the public product facts endpoint:
GET https://app.agenticorg.ai/api/v1/product-facts
The response contains version, agent_count, connector_count, and tool_count. Do not copy those values into documentation, page copy, or tests: they are computed from runtime registries and can change independently of a documentation release. The version declared for source builds is in pyproject.toml.
Billing limits and list prices come from core/billing/catalog.py. Production deployment behavior comes from scripts/deploy_cloud_run.sh.
Current release at a glance
Bring your own channels and AI credentials
New agents default to gemini-3.5-flash-lite; explicitly selected models remain
unchanged. Save your Google or other provider key in the protected AI credential
settings. Model selection, fallback and company scope remain configurable.
For this model, Agent Configuration > Gemini thinking offers an optional
medium profile for multi-step reasoning. Existing agents and generic calls keep
the provider default; no global flag or default is changed. The API equivalent is
llm.thinking_level="medium"; set it to null to restore the provider default.
Both runtime clients honor explicit profiles. Thinking is billed
as output tokens; budget for its additional token use and response time within
existing limits. It is not a correctness guarantee. Older model settings and all feature flags remain
unchanged. See reasoning acceptance.
The Channels dashboard connects your own WhatsApp Cloud API, Meta Messenger,
Telegram, Viber, inbound Mailgun email or signed gateway to an agent or workflow.
Credentials are encrypted, callbacks are authenticated, unlinked messages require
review, and private sender links delegate only your current permissions. Existing
Twilio voice/call setup and remote MCP tool discovery remain separate integrations.
Native channel replies default to optional status notices. Telegram agent
connections can opt into bounded final-answer replies for the linked private
sender under Channels > Reply content. Traces and tool-call records stay in
AgenticOrg; approvals, sender authorization and tenant controls still apply.
The encrypted intake carries the authenticated sender identity across services;
older receipts without that proof remain withheld, even if the agent completed.
For tool-free Telegram agents without traffic splits in this opt-in mode,
follow-ups may use up to four
recent, confirmed question/answer pairs from the same linked private sender and
agent/company scope, within 30 minutes. This is bounded text context, not durable
memory or permission to repeat actions. Hindi and other Unicode model input
remains readable before privacy scanning; existing redaction still applies.
With AGENTICORG_PII_HINDI_GRAMMAR_ENABLED=true (default off), targeted Hindi
grammar checks distinguish referential name/colour questions
from named values. This is not a general-purpose Hindi entity-recognition model;
quoted names, unknown words and structured identifiers retain privacy scanning.
Follow the channel account and workflow guide for account creation, callback registration, sender linking and verification. Local wire-contract tests are not proof of real provider-account delivery. Reuse an existing Telegram connection for an already connected bot; a second connection must not overwrite its webhook. Change its destination through Save settings only when authorized and no tasks are queued or running. Verify real model reasoning separately from transport-only workflows, and do not claim a combined Telegram-to-Gemini flow unless one delivery proves both.
Acceptance checks validate the actual answer as well as the terminal status. A completed, high-confidence model run can still be wrong; compare numeric results independently and preserve PII protections while diagnosing it. See the bounded production acceptance runbook.
The production platform currently includes governed agent/workflow execution, document ingestion with scanned-document OCR, signed Twilio voice with provider-managed STT/TTS, tenant-scoped browser RPA, Python and TypeScript SDKs, MCP/A2A surfaces, and the bounded Shopify-to-OACP commerce runtime. See the current product status for the exact shipped, configuration-dependent, and not-shipped boundaries.
External actions remain explicit. A voice provider, connector, browser script, buyer channel, payment rail, merchant system, or POS path is usable only when the target tenant has the required credentials, scopes, configuration, and provider approval.
Governed business cases
The repository includes a tenant-gated business onboarding case workflow with
read-only provider investigation, a cited memo, deterministic policy scoring,
screening dispositions, human review, and an auditable hand-off. Provider calls
are refused unless the active role agent, registered tools, exact local case
purpose, and delegated grant all authorize the call. This case-specific check
is strict even if general tool enforcement is in off or warn mode.
AgenticOrg pins grantex==0.7.1 and calls its enforcement check with the
grant token, connector, tool and any numeric amount. It does not pass a case id or case
purpose, so a token's case purpose and per-case caps are not checked on
this path. The role's case_purposes list is a local AgenticOrg control, and
pooled grants are not bound to one case. Decision and
analyst actions still require a signed-in human; API keys, agent tokens, and
MCP tools cannot act as that human. The case runtime is off for a tenant until
enabled and configured. This source description is not a claim that a particular
hosted deployment has enabled the workflow. See the case lifecycle and setup,
grant-enforcement runbook, and
decision requests.
Voice, email, OCR, and browser RPA can be exercised together before release with the Docker-backed local multichannel simulation. It uses fresh PostgreSQL, local Mailpit delivery, real Tesseract, and optional real Playwright Chromium while keeping paid calls and production mutations off.
Knowledge upload status distinguishes extraction from searchable indexing. With opt-in upload recovery, transient native embedding failures retry on the existing worker; the previous searchable copy remains until replacement succeeds. Malformed PDF/Office files are refused before replacement. See Knowledge and OCR for status meanings, citations and recovery limits. For a reasoning-only agent, disable suggested tools and leave tool/connector selection empty; this does not bypass tenant budgets. Provider charges and quotas still apply. Use structured output for confidence, keep review thresholds intact, and include explanation calls and provider retries in any test spending allowance. See Create agents and Run and chat for bounded acceptance steps and the opt-in direct-run explanation history.
The dashboard's Recent Activity queries audit records. The separate internal
live-feed pipeline persists events per tenant when published and can replay
them by sequence after a WebSocket interruption. Its only writer is the
conversation supervisor console (off by default behind
AGENTICORG_CONVERSATION_V2_ENABLED), which announces conversation changes
without message text for the Conversations screen; other operational event
writers are not wired to that pipeline. Its browser component exposes
connection/catch-up status without raw payload display; it is not mounted as
the dashboard's live stream. Broker reconnection, bounded socket fanout, and
periodic credential revalidation are covered by local tests. Production
latency, throughput, and availability remain unmeasured. The
activity delivery guide
explains the boundary. The scale and resilience assessment
tracks remaining connection-scale, load, and restore work; the
recovery guide separates planned targets from proven
production controls.
AI spend intelligence
AI spend intelligence measures AI spend in rupees against the organisation's
own structure. It is off by default behind
AGENTICORG_SPEND_INTELLIGENCE_ENABLED: while it is off,
GET /api/v1/spend/status answers enabled: false, every other spend route
returns 404 and nothing is metered. Phase 1 is API-only; the application has
no spend screen yet.
When a deployment turns it on, administrators keep the reference data spend is
measured against: an organisation tree, source mappings, model aliases,
effective-dated rate cards (a contract card ranks above a list card, with
cached-input prices, volume tiers and a stored batch discount that phase 1 does
not yet apply), FX rates that convert every price
to INR, and commitments. Every metered model call is written as usage records
with server-side attribution, priced at the rate card in force on its billing
date (or the deployment's list price for model tokens), and so are embeddings,
OCR pages, speech minutes, priced tool calls, storage GB-days and in-house GPU
node hours. Daily rollups, coverage
with the unattributed share, meter gaps and audited maintenance jobs sit on
these records. Provider invoices are imported and reconciled per billing month
within a 1% match tolerance; a difference is accepted with a reason by an
administrator other than the invoice importer. GET /api/v1/spend/gate
reports the Gate 1 status of a month: at least 98% of INR spend attributed to
a business unit, department, team or cost centre, with no unpriced,
unconverted or FX-pending record, and every provider reconciled within 1%.
flowchart TD
flag{"AGENTICORG_SPEND_INTELLIGENCE_ENABLED"}
flag -->|"off, the default"| off["Only GET /api/v1/spend/status answers, other spend routes are 404"]
flag -->|"on"| ref["Reference data: organisation tree, source mappings, model aliases, rate cards, FX to INR, commitments"]
usage["Model calls, embeddings, OCR pages, speech minutes, priced tool calls, storage GB-days, GPU node hours"] --> meter["Meter and writer: server-side attribution and pricing"]
ref --> meter
meter --> records["Usage records"]
records --> rollups["Daily rollups, coverage and the unattributed share"]
invoices["Imported provider invoices"] --> recon["Reconciliation per provider and billing month"]
records --> recon
recon -->|"outside the 1% match tolerance"| accept["Acceptance with a reason by a second administrator"]
rollups --> gate(["Gate 1 status: at least 98% attributed and every provider within 1%"])
recon --> gate
Rate cards, commitments, prices, invoices, reconciliations and the gate are answered only to a human administrator or auditor. Other readers see usage filtered by agent visibility and are refused tenant-wide figures. Spend dashboards, budgets, spend alerts, forecasting, statements and month close are later phases. See the user guide, the feature reference and the rollout runbook.
What is in this repository
| Area | Current implementation |
|---|---|
| Agent runtime | FastAPI and LangGraph runtime with model routing, tool invocation, confidence handling, retry policy, and persisted execution state |
| Agent authoring | Built-in agent definitions, custom agents, prompt templates, organization hierarchy, and a no-code UI |
| Workflows | Workflow definitions, runs, schedules, conditions, approvals, and audit events |
| Governance | Tenant and role boundaries, scoped tools, human-in-the-loop queues, shadow evaluation, policy checks, and kill-switch patterns |
| Integrations | Native connector registry plus optional integration gateways; actual availability depends on credentials, scopes, provider access, and tenant configuration |
| Knowledge and channels | Native and OCR document ingestion/search, reports, notifications, signed Twilio voice calls, RPA, and other configured channels |
| Developer access | REST API, Python SDK and CLI, TypeScript SDK, MCP server, legacy A2A-shaped task APIs, and source-implemented A2A v1 HTTP+JSON synchronous text |
| Commerce | Merchant-scoped Shopify read-only sync, OACP artifact intake/cache, buyer-safe answers, public catalog surfaces, prepared provider or POS handoffs, and flag-gated UCP and ACP surfaces (ACP feed, checkout sessions and order events) |
| Operations | PostgreSQL, Redis, object storage, observability hooks, migrations, security checks, and Cloud Run deployment tooling |
| AI spend intelligence | Off by default; API-only organisation tree, source mappings, rate cards, FX to INR, commitments, attributed usage records for model calls and non-token usage, daily rollups, coverage, invoice reconciliation, maker-checker acceptance, and the Gate 1 status |
A source definition is not evidence that a specific tenant has connected the provider or enabled write access. The Connectors page now separates registration from configured credentials and a recent, stale, failed, or missing health check. That evidence does not verify provider scopes, API contract coverage, sustained sync, or an error budget. Connector actions still require approved credentials, scopes, policies, and provider availability.
Capability status
Implemented in the platform
- Agent definitions and tenant-created agents
- Agent and workflow execution through authenticated APIs
- Human approval queues and configurable escalation conditions
- Audit records for governed runtime activity
- Prompt templates, organization structure, and role-aware application views
- Native connector definitions and a scoped tool gateway
- Public A2A and MCP discovery with authenticated execution paths
- Python and TypeScript client packages plus an MCP server package
- Hosted billing limits and checkout integration
- OACP commerce configuration, Shopify read-only sync, artifact caching, buyer channels, and safe handoff preparation
AgenticOrg MCP questions
How do I add AgenticOrg MCP to Claude Code?
Run claude mcp add agentic-org -- npx -y agenticorg-mcp-server in your terminal. Add --scope user to make it available in every project.
How do I add AgenticOrg MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does AgenticOrg MCP provide?
It exposes 16 tools, including list_agents, run_agent, get_agent_details, create_agent_from_sop, deploy_agent.
Is the MCP server free to use for companies?
Yes, the MCP server is open source under the Apache License 2.0 and is free for any use including commercial.
Do I need a commercial agreement to use the AgenticOrg platform?
Yes, any organization must sign a commercial agreement with Orchestrum Technologies LLP before using, testing, or deploying the platform.
Can individuals use the platform for free?
Yes, an individual's own personal use of the platform is free.