Skip to main content

gatecore-langchain

gatecore-langchain provides three LangChain tools for GateCore marketplace discovery and procurement, plus helpers that execute a procured capability through GateCore's signed gateway. The adapter contains transport and configuration only; GateCore services enforce identity, policy, trust, pricing, funding, delegation, and settlement.

The MCP tools support public full-mode GateCore endpoints only. read mode passes the server's fail-closed procurement error through unchanged. off mode is unsupported because it does not replace the adapter's legacy placeholder identity with the MCP credential identity.

Install from the GateCore monorepo

python -m pip install -e ./libs/sdk -e ./libs/adapters/gatecore-langchain

Install from PyPI

python -m pip install gatecore-langchain

Read the ten-minute public guide.

Configuration

Discovery is keyless. discover_listings and get_listing are public reads on the GateCore MCP endpoint: they need no key and no account, only the endpoint URL:

GATECORE_MCP_URL=https://mcp.gatecoreai.com/mcp

Procurement needs a GateCore MCP access key (gcmk_...). procure, list_procurements, and submit_lead are rejected without one, because agent identity and tenant scope come from the credential. This adapter's gatecore_procure tool is the one that needs it:

GATECORE_MCP_KEY=gcmk_...

A key that is set but malformed fails at toolkit construction; a key that is absent is only an error when a tool that needs one is called.

execute_procured and aexecute_procured validate these variables lazily on first use:

GATECORE_GATEWAY_URL=https://api.gatecoreai.com
GATECORE_BEARER_TOKEN=...
GATECORE_AGENT_ID=agent:example
GATECORE_ACCESS_GRANT_ID=grant:example
GATECORE_KEY_ID=key:example
GATECORE_PRIVATE_KEY_PATH=/secure/path/agent-key.pem

Set exactly one of GATECORE_PRIVATE_KEY_PATH or GATECORE_PRIVATE_KEY_PEM.

Quick start

Discovery is copy-paste complete and needs no key:

import os

os.environ["GATECORE_MCP_URL"] = "https://mcp.gatecoreai.com/mcp"

from gatecore_langchain import GateCoreToolkit

tools = GateCoreToolkit().get_tools()
for tool in tools:
    print(tool.name, "-", tool.description.splitlines()[0])

listings = tools[0].invoke({"query": "data"})  # keyless
print(listings[0]["listing_id"])

Procurement is the step that needs a key. A free Developer key (1,000 governed transactions a month, no card) is minted at app.gatecoreai.com/developer/portal; set it as GATECORE_MCP_KEY before calling gatecore_procure.

Procurement runs over GATECORE_MCP_URL and GATECORE_MCP_KEY alone. Executing a procured capability through the signed gateway uses execute_procured and the gateway variables above:

from gatecore_langchain import GateCoreToolkit, execute_procured

tools = GateCoreToolkit().get_tools()
procure_result = tools[2].invoke({"listing_id": "listing:example"})
decision = execute_procured(procure_result, {"query": "example"})

All tools are async-native through LangChain's async invocation methods. Their synchronous bridge uses asyncio.run() and therefore must not be called from a thread that already owns a running event loop; use ainvoke() in async applications.

Metadata

Release files for gatecore-langchain 0.1.4

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for gatecore-langchain 0.1.4
File Size Uploaded
gatecore_langchain-0.1.4.tar.gz 16.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for gatecore-langchain 0.1.4
File Interpreter ABI Platform
gatecore_langchain-0.1.4-py3-none-any.whl Python 3 none any Details

Total release size: 29.8 kB

Release files / gatecore_langchain-0.1.4.tar.gz

Download URL gatecore_langchain-0.1.4.tar.gz
Size 16.2 kB
Tags Source
SHA-256 checksum
How to use checksums
f57c640edf9de1c4500a2a011892a052ca68ae65c0c8a16ae2db338bbcef8ce0
BLAKE2b-256 checksum
How to use checksums
e413da71628bc378fa76e6a6b6784bb8ff59eb67f98bd2538d9c2a154d7e759d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 7, 2026.

Transparency log

Release files / gatecore_langchain-0.1.4-py3-none-any.whl

Download URL gatecore_langchain-0.1.4-py3-none-any.whl
Size 13.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
92acf5eddf7efa7f35e13bbadaf35f33ec365d62058b529640f3925209c6fbd6
BLAKE2b-256 checksum
How to use checksums
f44d2700147dec7a15e8c8d4ab90ce4172b199599280349ed8ff63aa9a14dd3e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 7, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.4 This release

2 release files

0.1.3

2 release files

0.1.2

2 release files

0.1.1

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page