med-lit-mcp
med-lit-mcp is an MCP server for medical literature reviews. It takes a review through four deliberate stages, search → screening → fetch → wiki, and ends with an evidence-linked wiki you can open in Obsidian.
Your MCP client's model does the reading and writing (screening decisions, entity extraction, syntheses). med-lit-mcp searches the databases (PubMed, PMC, OpenAlex, Europe PMC, Semantic Scholar, Scopus), stores everything, checks the model's work against the source text, and exports the wiki. Every screening decision, extracted mention and synthesis citation must be a verbatim quote or a reference to the stored text.
- Clients: Hermes (terminal and Desktop), Claude Code, Claude Desktop, Codex, pi and ChatGPT desktop Work/Codex.
- Platforms: Linux, macOS and Windows.
- Requirements: a contact email (
NCBI_EMAIL). No embedding endpoint, model API key or build step. - Bots: configure a scheduled literature bot from Hermes, Claude Code or Codex chat; Hermes runs the schedule, screens new articles and adds them to the wiki.
Install
The CLI routes need uv. Enter your email and database keys in the form or your own terminal, never in chat.
| Client | How |
|---|---|
| Hermes | Run uvx med-lit-mcp setup --client hermes, then /reload-mcp in Hermes and say “Set up med-lit.” Enter email and keys in the private local browser form. Needs uv. |
| Claude Code | Run uvx med-lit-mcp setup --client claude-code, start a new Claude Code session, then say “Set up med-lit.” Enter email and keys in the private local browser form. |
| Codex | Run uvx med-lit-mcp setup --client codex, start a new Codex session, then say “Set up med-lit.” Enter email and keys in the private local browser form. |
| pi | Run uvx med-lit-mcp setup --client pi, or the install script. Needs uv. See med-lit in pi. |
| ChatGPT desktop Work/Codex (macOS, Windows) | Run the install script with --chatgpt (Windows: -ChatGPT), then fill in the browser form |
| Claude Desktop | Install med-lit-<version>.mcpb from the latest release under Settings → Extensions, then switch it on |
The same script installs and updates; use --client hermes, --client claude-code or --client codex (Windows: -Client) to connect before configuring privately from chat. Credentials are stored in private local files and are not returned to the chat model. On the same computer and user account, these agents share med-lit's saved settings unless you choose separate configuration directories. See Setup for every client, manual registration and updating.
Use
Ask your agent a research question. med-lit leads it through the review one step at a time, and stops for every decision that is yours:
How are large language models used in shared decision making in healthcare? Do a basic review.
(the agent shows the mode and search settings, then the drafted search question) Looks good, run it.
(it reports the results and proposes inclusion and exclusion criteria, each with its reason) Approved.
(it screens, asks about the articles it could not decide, and replies with the answer and the full report)
There are three modes:
- basic screens titles and abstracts, then writes the report from the abstracts.
- full also fetches the included articles' full text and builds the evidence-linked wiki, then writes a report that can quote the full text.
- deep runs full mode in rounds, like a bot's runs in one session. After each round the agent judges whether the included studies answer the question; if not, a revised search aimed at the gaps adds the best new articles, which are screened, fetched and added to the wiki, until the evidence is enough or the round limit is reached.
The report is written for a reader who did not see the review: a short answer first, then the evidence by theme, how much to trust it, and how the review was done, with numbered references. Each cited study and quoted finding is checked against the stored articles, and the description of the search and screening comes from the review's own record. See Running a review.
You can also run each stage yourself ("Screen it. Include … exclude …", "Fetch the included articles and build the wiki"). Each review is a self-contained project folder. Open it in Obsidian with Open folder as vault.
What's new in 0.4.0
- Hermes, Claude Code and Codex connect before configuration. Ask “Set up med-lit” after installation; a private local browser form collects your email and database keys without adding them to conversation history. On a headless server, use the terminal setup there. The form opens separately from the chat UI and names the connected agent.
- Configure scheduled literature bots in a normal agent chat. Copy a tried review, approve the proposed schedule and limits, then change settings, pause, resume or archive it conversationally. Bots still require Hermes to run their schedules. Scheduled runs keep their restricted tools. Defaults for new reviews and bots are conversational too.
- Saved settings apply to the open connection. Changing or removing a key takes effect without restarting med-lit. Existing review settings stay unchanged when you change defaults for new reviews. Terminal setup and scripted email/folder arguments remain available.
- More reliable bot registration. Bots keep the launch command from the connected server, including development checkouts. Retrying a creation whose job ID was lost recovers the existing routine instead of creating a duplicate.
Live setup and bot-management checks passed with Hermes, Claude Code and Codex, using isolated settings and synthetic credentials. See the validation record.
What's new in 0.3.0
- Research modes: from a question to a report. Ask a research question and
research_nextleads the review step by step, stopping at every decision that is yours: the mode and search settings, the question, the criteria, whether to screen on, and the articles it could not decide.- basic: titles and abstracts; full: also full text and the evidence wiki; deep: full mode in rounds. After each round the agent judges whether the evidence answers the question (
record_evaluation) and, if not, a revised search adds the best new articles, until it is enough orresearch.deep_roundsis reached. - Inclusion and exclusion criteria come with reasons, each with a code (I1 … E1 …), and every exclusion names the criterion it rests on, so the report counts the reasons for exclusion.
- basic: titles and abstracts; full: also full text and the evidence wiki; deep: full mode in rounds. After each round the agent judges whether the evidence answers the question (
- A report that answers the question (
next_report,record_report), written for a reader who did not see the review: a short answer, the evidence by theme, how much to trust it, how the review was done, numbered references and an appendix with the quotations and criteria. Citations and quotations are checked against the stored articles; the description of the search and screening comes from the review's record. Each report gets its own file inreports/. - Fits Hermes as it works. Tool schemas are published without
$ref, so every argument states its type: Hermes passes$refto OpenAI-compatible models unresolved, and the model then sent the search question as a broken string (6 of 20 replayed calls before, 0 of 20 after). The call that ends a screening session returns the next step itself, for an agent that asks the researcher at once. - Fixed: an article stayed in
wiki_taskswhen a worker lowered its page allowance after recording its last page; deep-mode report portions now fit pi's 20 KiB tool results.
Tested on Hermes and pi, interactive and one-shot, in every mode: research modes test.
What's new in 0.2.1
- Install scripts replace the desktop installers.
scripts/install.sh(macOS, Linux) andscripts/install-windows.ps1(Windows) install and update med-lit for every terminal client, and with--chatgptfor ChatGPT desktop. They need uv. The signed macOS.dmgand the WindowsInstall med-lit.batare no longer built. The Claude Desktop.mcpbstays. setup --devstops with a clear message when uv is not onPATH, instead of registering a command that cannot start.
Documentation
| Topic | |
|---|---|
| Setup | Installing for each client, manual registration, updating |
| Configuration | Email, keys and environment variables; per-review settings and defaults |
| Running a review | Projects, how search, screening, fetch and wiki work, tools, the viewer |
| med-lit in pi | Registration, the optional pi package (research policy, scoped workers), recommended settings |
| Bots | Keeping a review up to date with Hermes scheduled jobs |
| The wiki | Obsidian, entity types, roles and relationships, Simple Graph Builder |
| Ontology | The full knowledge-graph contract and graph export format |
| Development | Running from a checkout, tests, compatibility |
| Installation and release | The install scripts, the Claude Desktop extension, releasing |
| Validation | Platform test records, including the earlier desktop installers |
License
med-lit-mcp is licensed under the PolyForm Noncommercial License 1.0.0. You may use, modify and share it for any noncommercial purpose, including research, teaching, and use by educational institutions, public research organizations and public health organizations. Commercial use needs a separate license; open an issue to ask. NOTICE records the MIT-licensed origin of the search engine.
Metadata
Release files for med-lit-mcp 0.4.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| med_lit_mcp-0.4.0.tar.gz | 345.0 kB | With provenance | Details for med_lit_mcp-0.4.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| med_lit_mcp-0.4.0-py3-none-any.whl | Python 3 | none | any | Details for med_lit_mcp-0.4.0-py3-none-any.whl |
Total release size: 550.7 kB
Release files / med_lit_mcp-0.4.0.tar.gz
| Download URL | med_lit_mcp-0.4.0.tar.gz |
|---|---|
| Size | 345.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
2322c8e800467c20f96a99a341c7fa537627bf68a0bb3a050c94f398a65ece5a
|
|
BLAKE2b-256 checksum How to use checksums |
483e1e598bff8e9e509a975c49d0e5ca90079b9a4f2beaecae35841f7c1dad0d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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 Nov 9, 2026.
Transparency logRelease files / med_lit_mcp-0.4.0-py3-none-any.whl
| Download URL | med_lit_mcp-0.4.0-py3-none-any.whl |
|---|---|
| Size | 205.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
57af03068086b284b07a5de60c7396769ed1dafc09f4b672c2b789f25af86e74
|
|
BLAKE2b-256 checksum How to use checksums |
f2095798a91246f0fb826b141e93615f43d01b178cf283f98d82b12a4108796e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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 Nov 9, 2026.
Transparency logSecurity for med-lit-mcp 0.4.0
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.
Attestation for med_lit_mcp-0.4.0.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 Nov 9, 2026.
Transparency logA 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.