Skip to main content

remembra-mcp

Starts the Remembra MCP server over stdio. It is a launcher: installing it installs remembra[mcp] at the same version, and the remembra-mcp command runs remembra.mcp.server.

REMEMBRA_URL=https://api.remembra.dev REMEMBRA_API_KEY=rem_... uvx remembra-mcp
Variable Required Meaning
REMEMBRA_API_KEY yes Your API key (dashboard, Settings > API keys). Keep it secret.
REMEMBRA_URL yes https://api.remembra.dev for the hosted service, or your own server. Unset, it falls back to http://localhost:8787.
REMEMBRA_AGENT_ID no The name this agent's handoffs are recorded under, e.g. claude-code or codex. With a key scoped to one agent, handoffs are recorded under that agent and show as key-verified (a different name here is refused); otherwise the name is self-declared.

The tools let an agent read the brief another agent left for a repository (session_brief) and leave its own handoff when it stops (close_session), alongside memory store and recall. Source, docs and issues: https://github.com/remembra-ai/remembra

Metadata

Release files for remembra-mcp 0.17.2

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

Source distribution (sdist)

Source distribution for remembra-mcp 0.17.2
File Size Uploaded Provenance Actions
remembra_mcp-0.17.2.tar.gz 2.7 kB With provenance Details for remembra_mcp-0.17.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for remembra-mcp 0.17.2
File Interpreter ABI Platform Actions
remembra_mcp-0.17.2-py3-none-any.whl Python 3 none any Details for remembra_mcp-0.17.2-py3-none-any.whl

Total release size: 5.4 kB

Release files / remembra_mcp-0.17.2.tar.gz

Download URL remembra_mcp-0.17.2.tar.gz
Size 2.7 kB
Tags Source
SHA-256 checksum
How to use checksums
1a280d79b48287aadd79187731d167e1c0b98fe557aa851ee4781c53f3647f5c
BLAKE2b-256 checksum
How to use checksums
d76761ef6490c21d5228b90973da6e51cc05da61614e74c5aba9c3e80474db83
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 25, 2026.

Transparency log

Release files / remembra_mcp-0.17.2-py3-none-any.whl

Download URL remembra_mcp-0.17.2-py3-none-any.whl
Size 2.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
5c3fb8e9dcbe4348ebf23c1c667eca5e14a670dc4c93e9ea00d445bb917bb919
BLAKE2b-256 checksum
How to use checksums
1ff3699d1b7011d7590d1f87df6cae4ae1195cbd97b81a3796ae55dbf579a448
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 25, 2026.

Transparency log

Security for remembra-mcp 0.17.2

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.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for remembra_mcp-0.17.2.tar.gz

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 25, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

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