Mellos Mapping vs ROBINS I V2 MCP
A side-by-side look at the Mellos Mapping and ROBINS I V2 MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Mellos Mapping for developer tools work as a local process; choose ROBINS I V2 MCP for developer tools as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Mellos Mapping when
- You need dedicated capabilities in the Developer Tools domain.
- You prefer a local stdio subprocess transport.
- You want tools like
mmap_declare, mmap_update, mmap_read.
Choose ROBINS I V2 MCP when
- You need dedicated capabilities in the Developer Tools domain.
- You prefer a local stdio subprocess transport.
- You want tools like
get_spec, parse_document, parse_pmcid.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Developer Tools | Developer Tools |
| Quality signal | 67/100 · Great | 55/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 114 | 0 |
| Directory activity | 2 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 8 | 9 |
| Full listing | View Mellos Mapping | View ROBINS I V2 MCP |
Tools & capabilities
Mellos Mapping tools 8
mmap_declareGrow the Mellos map: set the title and diagram kind, add layer bands, lanes and groups (labeled subsystems within ONE band — declare them when a single band grows crowded, roughly five or more nodes in that band; a group must be a strict subset of its band, and a map spread thin across many bands needs none), add nodes, add dependency edges. Declare the missing design after reading existing pages with mmap_read; reuse verified nodes. Edges must point strictly downward (a node may only use nodes on lower layers); the batch is all-or-nothing. Title and kind can also be changed with mmap_update; this legacy form remains supported. Revising what already exists (moving, renaming, relabeling, clearing) is mmap_update.mmap_updateThe revision tool, all-or-nothing. Record progress on nodes: in-progress when starting a node (the pane spins), done with evidence when its verification passes, regressed with evidence when a done node breaks. Revise what the ghost design got wrong: move a node to another band, join or leave a group or lane, rename a band (or re-rank it, which reorders the whole map), relabel a group or a lane. Every clearable field takes null to empty it — that is how a field is cleared, never an empty string. Bands, groups and lanes are applied before the node updates, and within one node update `layer` moves the node before its other fields. The map is a ledger: report honestly, it never blocks you.mmap_readRead existing pages before creating a map. Returns structured IDs, revisions and bounded results. pages lists summaries; map reads page metadata/context; nodes/edges/layers/groups/lanes read editable records; neighborhood reads related nodes; changes compares saved source hashes with local files. New conversations and compacted context should resume the existing effort. mmap_view remains the picture.mmap_batchAtomically combine additions, updates and removals on ONE page. Checks the final graph, so a coordinated move or edge replacement needs no intermediate saves. Read IDs and revision with mmap_read first. Cross-page deletion is excluded.mmap_removeRemove edges, nodes, groups and empty layer bands (in that order, all-or-nothing). Removing a node also removes every edge touching it; removing a group merely ungroups its members. Use when the ghost design turns out wrong — the map is a hypothesis, revising it is honest work. `pages` is the other scale: it DELETES whole page files, so a finished effort can be cleaned up instead of accumulating tabs forever. A bare `{pages: ["slug"]}` with no other field is the normal form; combined with map edits, the edits are applied first and the pages are deleted after. The deletion is permanent and cannot be undone, so delete only pages whose effort is over — and only ever with the user behind it. An unknown slug is refused with the project's real page list (naming a page that does not exist is a typo, not a request). The default page has no slug and is not deletable here. A node elsewhere still pointing at a deleted page with `submap` stays legal — a submap reference has no existence invariant — but it has nowhere to dive until the page comes back.mmap_setupGet or set the mapping policy — WHEN the assistant opens a Mellos map. Call with no arguments to read it: the reply names the policy chosen for the USER (every project), the one this PROJECT overrides it with if any, and which of them is in effect. If it reports "not set", ask the USER to choose (never pick for them): always = map every structured task — workflows, designs, architecture, technical dependencies; complex = map only medium or complex tasks — several modules, a new subsystem, roughly an hour or more; on-request = map only when the user explicitly asks. Then call again with their choice to persist it. It defaults to user scope, which is the normal one — the question is about how someone works, so it is asked once ever, not once per repository. Pass scope: "project" only when the user wants THIS project to differ from that habit. The policy guides you; it never blocks the tools, and an explicit user request for a map always wins.mmap_viewRender the current Mellos map as monochrome text — the same picture the split-pane watcher shows live. Use it to check the map state or to show it inline in conversation. Every response ends with a `pages:` line naming the pages this project actually has and which one you are looking at, so this is also how you discover whether a map exists at all and under which slugs — never probe the files.mmap_openFor automatic display beside the current ChatGPT desktop conversation in Codex mode, use surface: "web-terminal", then call open_in_codex with the returned browser hostOpen object. No paste or Computer Use is needed. For the native host terminal, use surface: "codex-terminal": prepare absolute watcher commands for the current project, then ask the host to open its right terminal. This does not launch the watcher or type into that terminal. Agent exec PTYs cannot be attached using their numeric session ids. For a document panel, use surface: "markdown": generate MD + SVG files, enable automatic preview updates after successful map writes, then use the HOST file-opening tool to display the returned absolute Markdown path on the right of the current conversation. Generated does not mean visible: this server cannot open or observe the desktop side panel. For interactive maps, choose surface: "web": start or reuse a project-local web viewer and pass the returned URL to the host browser-opening tool. Markdown and terminal remain available. The default surface is "terminal", preserving the terminal workflow. Put the live map on the user's screen: a terminal pane beside this conversation that redraws on every write. Call it whenever a result says `pane: CLOSED` — and do NOT ask permission first, because a user who has set a mapping policy has already said they want to see the map. With a pane already open this RETARGETS it to `page` instead of opening a second one, so it is also how you show the user a particular page when they ask for one. It never closes a pane: taking the map off the screen belongs to the user (the `q` key in the pane, or typing `mmap` in a terminal). The reply says whether a pane actually reported itself in afterwards, not merely that a command was run. Automatic terminal opening supports Windows Terminal, tmux on Linux/macOS, and Pebrel, which splits the conversation's own pane. omp (Oh My Pi) has no side panel of its own: there the routes are this same terminal pane (a Windows Terminal split, or a tmux split on Linux/macOS) and the web viewer, whose URL the session opens with its own browser tool. If opening fails, relay the reason and copyable command; retry only after the environment changes or the user asks.
ROBINS I V2 MCP tools 9
get_specReturn the encoded ROBINS-I V2 specification: 13 preliminaries, 40 signalling questions across 6 domains (domain 1 in two variants), the response vocabularies, the evidence policy, and the algorithm fingerprint. OPTIONAL in the assessment flow — introspection only. assess_result already carries the rubric for the domain in hand, so calling both duplicates the payload. detail='compact' (default) gives question ids, own-words labels, response options and evidence modes; detail='full' adds every intent and assessor note. The descriptions are this implementation's own wording, NOT the published signalling-question text, which is not redistributable. The published question IDs are what make the output interoperable.parse_documentPRIMARY entry point: parse a study report into a bundle with character-offset, source-tagged section spans. Every quote you later cite is resolved against THIS text, and every claim of absence is searched in it. PASS `citation=`: the full bibliographic reference in APA style. It appears on the rendered assessment so the study being judged is unambiguous. `document` is EITHER the raw text OR a file path — but the path must be readable on the SERVER host. If your files live on your own filesystem, paste the TEXT instead, or use parse_pmcid for an open-access PMCID. A path-looking string the server cannot find raises rather than being ingested as its own text. PASS THE SUPPLEMENT WHEN YOU HAVE IT. `supplements` is a list of server-readable paths merged as supplementary material. This matters more for ROBINS-I than for a reporting audit: the target-trial specification that settles C1-C4, and the analysis detail domains 1 and 4 turn on, routinely live only in the appendix. Without it those questions read NI when the answer was merely in a file nobody passed. supplement_status defaults to 'user_provided' when supplements are given; pass 'none_exists' to assert the article has none. Returns the section map, the text hash that keys later calls, and a cue survey — hit counts for the 15 evidence patterns, so you can see before reading where each domain's evidence lives and which absences already look real.parse_pmcidCONVENIENCE entry point: retrieve an open-access article from Europe PMC by PMCID and parse it, main text plus PMC-hosted supplements, merged into one source-tagged bundle. Use it when you have no file in hand, or to auto-fetch an open-access paper's supplement; for a manuscript you were given, use parse_document. supplement_status is 'retrieved' when a supplement was obtained, else 'not_retrieved' — a supplement may still exist on the publisher site, so absence of retrieval is never proof of absence. Raises if no open-access full text is available. An APA-style citation is built from the article's JATS metadata; pass citation= to override it.set_prespecified_confoundersSupply P1 — the confounding factors this REVIEW judges important for the intervention-outcome relationship, listed before any study is assessed. THIS IS BLOCKING. Domain 1 will not be scored without it. Question 1.1 asks whether all IMPORTANT confounding factors were controlled for, and 'important' is defined by this list, not by the paper's covariate table. Substituting the paper's own list would let the study grade its own confounding control, which is exactly the judgement ROBINS-I asks the reviewer to make independently. 'Important' means adjustment would be expected to change the estimate meaningfully; factors with only very weak associations are excluded. You MAY propose a list from domain knowledge or a DAG — that is useful and is what this parameter is for — but a proposed list is not a ratified one. Leave `ratified_by` empty unless a human in this conversation has actually reviewed and accepted the list; the assessment then carries P1 in its ratification queue and is explicitly not final until they do. Do not sign it off on their behalf. Scoped by `review_id` because P1 belongs to the review, not to one study: the same list applies to every result assessed under it.specify_resultName the ONE numerical result being assessed, and settle C4. Required before any domain can be scored. ROBINS-I assesses a single effect estimate, not a paper. A study reporting three outcomes across two analyses yields six assessments; give each its own `result_id` and run them separately. `accounts_for_deviations` IS C4, and it is the highest-leverage input here: it swaps domain 1's entire question set and algorithm, so it cannot be deferred until domain 1 is reached. 'no_itt' — the analysis does NOT account for switches between the compared strategies or other protocol deviations. It targets the effect of assignment. Domain 1 variant A (baseline confounding only). 'yes_pp' — the analysis DOES account for them, by censoring, follow-up partitioning, or a g-method. It targets the effect of sustained receipt. Domain 1 variant B (baseline AND time-varying confounding). Judge this on what the ANALYSIS DOES, not on the label the authors give their estimand. A paper whose protocol table says 'observational analogue of the per-protocol effect' but which never censors at deviation is 'no_itt'. Getting this wrong means answering five questions that do not apply. `result_assessed` is A1: the estimate with its precision. `outcome` is A3. `result_location` (A2) is where it appears and why it was chosen. `target_trial` is C1-C3 as a dict of labelled strings — eligible participants, intervention strategy, comparator strategy, and any note on the estimand. `information_sources` is D1: what you actually read. An NI answer is only defensible relative to what was searched. `b1`/`b2`/`b3` are the section B screening answers (Y/PY/PN/N). b1: was any attempt made to control confounding in this result? b2 (asked only if b1 is PN/N): is the potential for confounding great enough that an unadjusted result should not be considered further? b3: is the outcome measurement method unsuitable for the outcome it is meant to capture? Y/PY on b2 or b3 sends the result straight to critical and no domain is scored.assess_resultReturn the assessment scaffold for ONE domain: the questions actually in play, their own-words intent, the response vocabulary each accepts, what evidence each answer must carry, and the cue searches already run against this bundle with their hits. THE SCAFFOLD IS PER DOMAIN BY DESIGN. Most signalling questions are unreachable on any given path — 24 of 41 were never reached on the reference assessment — and which of domain 1's two question sets exists at all is decided by C4. There is no flat 41-question rubric to fetch, and asking for one would mean answering questions the algorithm discards. domain=0 (default) returns the overview: the preliminaries, what is settled, which domains are done, and which are outstanding. domain=1..6 returns that domain's scaffold. Domain 1 is refused until P1 is set. Work a domain at a time: read the cues to find where the evidence is, answer only the questions the algorithm reaches, then submit_answers. You do not state a judgement — the server computes it from your answers.submit_answersSubmit one domain's signalling-question answers and get back the COMPUTED domain judgement, or (domain=0) finalize the assessment. Each element of `answers` is one question: `question`, `response`, `evidence_mode`, `rationale`, plus the evidence that mode requires — `quotes` for manuscript_positive, `search_cue` or `search_terms` for manuscript_absent, `prior_ref` for reviewer_prior. Answer only the questions the algorithm reaches; omit the rest rather than answering NA. `support` is your narrative for the domain as a whole and appears in the report. Three things are enforced here, and all three are the point of the tool: every quote is resolved to character offsets in the ingested bundle and an unresolvable one is REJECTED with the nearest text found; every claim of absence is backed by a search THE SERVER runs, so it is reproducible; and the judgement is computed by the published algorithm from your answers, never asserted by you. If the traversal reaches a question you did not answer, the call returns status='incomplete' naming it — supply it and call again. `override_judgement` sets the domain judgement against the algorithm and REQUIRES `override_justification`. Overrides cannot hide: the report shows both values and the override enters the ratification queue. domain=0 finalizes: it computes the overall judgement (worst of the six domains by default), assembles the stamped assessment and returns the rendered report inline. `overall_escalate` applies the tool's permitted escalation — several moderates to serious, or several seriouses to critical — and requires a justification. The returned `report` is THE ARTIFACT OF RECORD: present that, not a table of your own, and repeat its ratification queue if it is non-empty, because an assessment with unratified items is not final.render_reportRe-render a finalized assessment as a self-contained HTML page — the meta panel, the six-domain summary strip, the per-domain judgement with its algorithm trail and the evidence behind every answer, styled to the Black Swan Causal Labs identity and carrying the provenance stamp. Returns the HTML in `html` (display it inline or publish it as an artifact) and the same bytes base64-encoded in `content_base64` (decode and save as .html). This is a pure re-render of the artifact submit_answers already stamped — nothing is re-scored. The assessment must have been finalized this session; the cache does not survive a server restart.export_robvisCombine assessment RECORDS from any number of runs into a CSV for **robvis** (McGuinness & Higgins), the standard tool for Cochrane-style risk-of-bias figures. A review of 200 studies is 200 separate runs — each assessment costs a session, and nothing in this server survives between them. So pass `records`: the `record` object each submit_answers(domain=0) returns. They are small, flat and JSON-native, so a whole review's worth fits in one context, and they carry their own provenance so every row stays traceable to a document and an algorithm fingerprint. Omit `records` to use only what was assessed in THIS session (convenient, but session-scoped). READ THE RETURNED `losses` BEFORE PUBLISHING THE FIGURE. It reports records that are not yet ratified, mixed C4 variants, equal weighting, and records built under differing algorithm transcriptions — each of which would make the figure claim more than the assessments support. This is not a column dump, because robvis's ROBINS-I template is ROBINS-I **V1** and V2 is not drop-in compatible: * V1 has SEVEN domains and orders selection of participants BEFORE classification of interventions. V2 has six and swaps that pair. Writing V2's columns out in order loses no data and raises no error — it just prints your classification judgement under the heading "Bias due to selection of participants". layout='robins_i' (the default) places each V2 judgement into its correct V1 SLOT and marks the dropped deviations domain NA. Upload it with tool='ROBINS-I'. * layout='generic' writes six columns headed with V2's own domain names, for tool='Generic'. The headings are then right, but robvis relabels the judgements into ROB1's vocabulary — Moderate becomes "Some concerns", Serious becomes "High". Prefer 'robins_i'. Neither layout can carry 'Low, except for concerns about uncontrolled confounding': robvis reduces every cell to its first initial over a five-fill palette, so it collapses to Low whatever string is written. Say so in the figure caption.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Mellos Mapping
{
"mcpServers": {
"mellos-mapping": {
"command": "npx",
"args": [
"-y",
"mellos-mapping"
]
}
}
}
ROBINS I V2 MCP
{
"mcpServers": {
"robins-i-v2-mcp": {
"command": "uvx",
"args": [
"robins-i-mcp"
]
}
}
}
Frequently asked questions
Mellos Mapping is categorized under Developer Tools and uses a local stdio subprocess. ROBINS I V2 MCP belongs to Developer Tools and uses a local stdio subprocess. Pick Mellos Mapping for developer tools work and ROBINS I V2 MCP for developer tools.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Mellos Mapping has no declared pricing — check the project's own site. ROBINS I V2 MCP has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add mellos-mapping and robins-i-v2-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Mellos Mapping has a quality signal of 67/100 (Great) with 2 views, 0 installs and 114 GitHub stars. ROBINS I V2 MCP has 55/100 (Good) with 1 views, 0 installs and 0 GitHub stars.