langchain-taiga
This package provides Taiga tools and a toolkit for use with LangChain. It includes:
create_entity_tool: Creates user stories, tasks and issues in Taiga.search_entities_tool: Searches for user stories, tasks and issues in Taiga.get_entity_by_ref_tool: Gets a user story, task or issue by reference.update_entity_by_ref_tool: Updates a user story, task or issue by reference.add_comment_by_ref_tool: Adds a comment to a user story, task or issue.add_attachment_by_ref_tool: Adds an attachment to a user story, task or issue.
Installation
pip install -U langchain-taiga
Environment Variable
Export your taiga logins:
export TAIGA_URL="https://taiga.xyz.org/"
export TAIGA_API_URL="https://taiga.xyz.org/"
export TAIGA_USERNAME="username"
export TAIGA_PASSWORD="pw"
export OPENAI_API_KEY="OPENAI_API_KEY"
If this environment variable is not set, the tools will raise a ValueError when instantiated.
Usage
Direct Tool Usage
from langchain_taiga.tools.taiga_tools import create_entity_tool, search_entities_tool, get_entity_by_ref_tool, update_entity_by_ref_tool, add_comment_by_ref_tool, add_attachment_by_ref_tool
response = create_entity_tool({"project_slug": "slug",
"entity_type": "us",
"subject": "subject",
"status": "new",
"description": "desc",
"parent_ref": 5,
"assign_to": "user",
"due_date": "2022-01-01",
"tags": ["tag1", "tag2"]})
response = search_entities_tool({"project_slug": "slug", "query": "query", "entity_type": "task"})
response = get_entity_by_ref_tool({"entity_type": "user_story", "project_id": 1, "ref": "1"})
response = update_entity_by_ref_tool({"project_slug": "slug", "entity_ref": 555, "entity_type": "us"})
response = add_comment_by_ref_tool({"project_slug": "slug", "entity_ref": 3, "entity_type": "us",
"comment": "new"})
response = add_attachment_by_ref_tool({"project_slug": "slug", "entity_ref": 3, "entity_type": "us",
"attachment_url": "url", "content_type": "png", "description": "desc"})
Using the Toolkit
You can also use TaigaToolkit to automatically gather both tools:
from langchain_taiga.toolkits import TaigaToolkit
toolkit = TaigaToolkit()
tools = toolkit.get_tools()
MCP server (Claude CLI & GitHub Copilot Chat)
The package now ships with a Model Context Protocol server powered by
fastmcp. It exposes the same Taiga tools without changing their
behaviour.
-
Ensure the Taiga environment variables above are set for the process running the server.
-
Start the server:
python -m langchain_taiga.mcp_server
-
Point your MCP client at the command:
-
Claude CLI/Desktop: add to
~/.config/claude/claude.jsonunder"mcpServers":{ "mcpServers": { "taiga": { "command": "python", "args": ["-m", "langchain_taiga.mcp_server"] } } }
-
GitHub Copilot Chat (CLI/IDE): add a similar entry to your Copilot MCP configuration, pointing to
python -m langchain_taiga.mcp_serverso the client can discover the Taiga tools.
-
The server exports the following tools for MCP clients: create_entity_tool, search_entities_tool, get_entity_by_ref_tool,
update_entity_by_ref_tool, add_comment_by_ref_tool, and add_attachment_by_ref_tool.
Tests
If you have a tests folder (e.g. tests/unit_tests/), you can run them (assuming Pytest) with:
pytest --maxfail=1 --disable-warnings -q
License
Further Documentation
-
For more details, see the docstrings in:
taiga_tools.pytoolkits.pyforTaigaToolkit
-
Official Taiga Developer Docs: https://docs.taiga.io/api.html
-
LangChain GitHub for general LangChain usage and tooling.
Metadata
Release files for langchain-taiga 1.7.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| langchain_taiga-1.7.0.tar.gz | 22.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| langchain_taiga-1.7.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 45.8 kB
Release files / langchain_taiga-1.7.0.tar.gz
| Download URL | langchain_taiga-1.7.0.tar.gz |
|---|---|
| Size | 22.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
7937e159522738ac482c033f005ef7dc18c37b46e06a7dac5e70c1eb211e6f58
|
|
BLAKE2b-256 checksum How to use checksums |
49c21244a4d3f4344abb6d1ca96815809a95531678914781b1c65302bf51762b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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 Feb 7, 2026.
Transparency logRelease files / langchain_taiga-1.7.0-py3-none-any.whl
| Download URL | langchain_taiga-1.7.0-py3-none-any.whl |
|---|---|
| Size | 23.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ada420df54caff8f0e01c04ecdb2ac7bd718b060fe7f84eb13882d3d11c279ad
|
|
BLAKE2b-256 checksum How to use checksums |
fef4ed147d4837e399a0baef3c8d625353b6f825c5a562c47875725bcbe4b32b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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 Feb 7, 2026.
Transparency log