Evidence vs Next AI Draw IO
A side-by-side look at the Evidence and Next AI Draw IO MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Evidence for developer tools work as a local process; choose Next AI Draw IO 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 Evidence when
- You need dedicated capabilities in the Developer Tools domain.
- You prefer a local stdio subprocess transport.
- You want tools like
issue_receipt, verify_receipt, record_disclosure.
Choose Next AI Draw IO when
- You need dedicated capabilities in the Developer Tools domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You want tools like
get_drawing_guide, get_shape_library, start_session.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Developer Tools | Developer Tools |
| Quality signal | 63/100 · Good | 72/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | API key required |
| Pricing | Not declared | BYOK (pay the provider) |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 1 | 36,373 |
| Directory activity | 3 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | 9 | 16 |
| Full listing | View Evidence | View Next AI Draw IO |
Tools & capabilities
Evidence tools 9
issue_receiptIssue an x402 offer-receipt (EIP-712) plus a Tersign compliance record (returned as `compliance`; verify_compliance_record checks it) for a payment that has ALREADY settled; when a ledger is configured, the ledger counter-signs the receipt into your hash chain, while the compliance-fields record is not counter-signed and is bound to its receipt only by your own signature, which covers the receipt's digest. Use this for money that moved; use record_disclosure for a non-payment agent action. Side effects: signs with your signing key (the one set in the Tersign plugin's settings in Claude Code, or the TERSIGN_* environment variables, else the one generated and kept locally on first run), and performs ONE network write to the ledger when a ledger URL, API key and seller id are set there too (without them it signs locally and returns an unchained artifact). Returns the signed receipt artifact, its keccak256 canonical digest, and — when chained — the ledger counter-signature and sequence number.verify_receiptVerify an x402 offer-receipt artifact, fully OFFLINE (no network, no API key, no account; checks no ledger or chain): recover the address whose key produced its EIP-712 signature over the six signed payload fields (version, network, resourceUrl, payer, issuedAt, transaction), and compute its canonical digest (the content address a ledger records it under). Recovery yields SOME address for any payload, so without expectedSigner the signer is UNAUTHENTICATED: valid:true then proves neither who signed nor that the receipt is unmodified — an edited receipt recovers a different address and still returns valid:true. Pass expectedSigner, the issuer's address obtained out-of-band, to bind it: valid:true then means the signed fields were signed by that key; a mismatch returns valid:false with the recovered signer so you can see who actually signed. Use this for a receipt (money); use verify_compliance_record for the compliance record issue_receipt returns beside a receipt. Returns { verdict, valid, signer, signerStatus: BOUND | UNAUTHENTICATED | MISMATCH, signerBound, testKey? (the signer is a PUBLISHED test key — anyone can sign as it), digest, unsignedFields? (present in the artifact but not covered by the signature), reason? }. Read verdict first.record_disclosureOne-call disclosure evidence (EU AI Act Art 50 dialect): digests the disclosure text LOCALLY, signs an action record with your key, and the public ledger counter-signs it into your per-signer hash chain. No API key needed — the first call self-provisions a free signer-keyed account, except when your key is already registered to an API-key account (409) or the daily provisioning caps are reached (429; https://tersign.ai/pricing).verify_compliance_recordVerify ONE record type: the compliance record that issue_receipt returns beside a receipt (`compliance`: a ComplianceRecordV1 `record` plus its ComplianceAttestation `attestation`, EIP-712 domain "compliance-fields"), fully OFFLINE (no network, no API key, no account): recompute the record's canonical digest, check that the attestation's signed payload names that exact digest and the same receiptDigest as the record, and recover the address that signed the attestation. It does NOT verify the disclosure record record_disclosure returns: that is a different record type (an action record, EIP-712 domain "tersign action-record"), and passed here it fails with a digest mismatch that says nothing about tampering. Use verify_receipt for the payment receipt itself. Without expectedSigner the signer is UNAUTHENTICATED and valid:true proves internal consistency only — anyone can edit a record, recompute its digest and re-sign the attestation with their own key, and still get valid:true with a different signer. Pass expectedSigner, obtained out-of-band, to bind authorship. Returns { verdict, valid, signer, signerStatus: BOUND | UNAUTHENTICATED | MISMATCH, signerBound, testKey? (a PUBLISHED test key — anyone can sign as it), digest (the recomputed record digest), reason? }. Read verdict first.record_refundLog a refund against a receipt already on your chain, as the SELLER. The ledger stores it as a PENDING refund entry that references the original receipt digest; the entry is NOT counter-signed or appended to the hash chain, and it has no digest or sequence number of its own. Nothing is edited or deleted: the original receipt and its chain position stay exactly as they were. Requires a ledger URL, API key and seller id (the Tersign plugin's settings in Claude Code, or the TERSIGN_* environment variables) and performs one network write; errors if the original digest is not on your chain. This RECORDS a refund you have already made — it moves no money. For a signed refund RECORD, build a compliance record with refundOf set to the original record digest (buildMinimalRecord in the SDK). Returns { id, status: "pending" }.open_disputeOpen an objective dispute against a counter-signed receipt as the PAYER (the configured key must be the receipt payer). Reasons: not_delivered, wrong_content, duplicate_charge. Contested non-mechanical claims escalate to the arbiter; duplicate_charge is decided instantly from ledger arithmetic.submit_dispute_evidenceSubmit signed evidence to an open dispute. Claimant evidence must be signed by the payer key; respondent evidence additionally requires the seller API key (the Tersign plugin's settings in Claude Code, or the TERSIGN_* environment variables).adjudicate_disputeTrigger deterministic adjudication of an open dispute: the same inputs always produce the same verdict and rationale — no discretion, no model in the loop — and the verdict object embeds the inputs it was computed from. Side effects: writes the verdict to the dispute record; a refund verdict also logs a PENDING refund entry against the receipt (not counter-signed into the chain; no money moves). Adjudicating twice is not meaningful; the first verdict stands (a second call returns 409). Returns the verdict, the rationale naming the rule applied, the adjudication inputs, the verdict digest, and the ledger signature over that digest.get_disputeFetch a dispute in full: its state, both sides' evidence references, the verdict and rationale once adjudicated, and the ledger signature over the record. Read-only — one network read, no key required, and safe to poll while a dispute is open.
Next AI Draw IO tools 16
get_drawing_guideReturn the drawing guide: XML format, layout, edge routing, style and editing rules. start_session already returns it; call this only if the guide is no longer in your context. With topic, returns a short XML reference for tables, layers or groups.get_shape_libraryGet the style syntax and shape names of a draw.io icon library. Call this BEFORE drawing with cloud, network or other icon shapes, and use the exact names it returns; never guess them. Libraries: - Cloud: aws4, azure2, gcp2, alibaba_cloud, openstack, salesforce - Networking: cisco19, network, kubernetes, vvd, rack - Business: bpmn, lean_mapping - General: flowchart, basic, arrows2, infographic, sitemap - UI/Mockups: android, material_design - Enterprise: citrix, sap, mscae, atlassian - Engineering: fluidpower, electrical, pid, cabinets, floorplan - Icons: webiconsstart_sessionStart a new diagram session, or continue a saved one with session_id, and open the browser for real-time preview. Starts an embedded server and opens a browser window with draw.io. The browser will show diagram updates as they happen. The result includes the drawing guide; follow it when drawing.list_saved_diagramsList the diagrams saved by earlier sessions (auto-save files), newest first, with their pages. Continue one with start_session session_id=<id>; the file path also works with load_diagram.create_new_diagramCreate a NEW diagram, REPLACING the whole document: every page and any unsaved user changes (the previous state stays in History). To add a tab use add_page; to change cells use edit_diagram. Before using icon shapes (AWS, Azure, GCP, Kubernetes, Cisco...), call get_shape_library first. Follow the drawing guide returned by start_session (call get_drawing_guide if it is no longer in your context). Pass screenshot: true on the last call of a complex diagram to check the result. Accepted xml: 1) Only the mxCell elements of one page (recommended). The server adds <mxfile>, <mxGraphModel>, <root> and the root cells "0" and "1": <mxCell id="2" value="Shape" style="rounded=1;" x="40" y="40" w="120" h="60"/> 2) A bare <mxGraphModel> with <root> (one page). 3) A full <mxfile> with one or more <diagram> pages. Every page's <root> must start with <mxCell id="0"/><mxCell id="1" parent="0"/>. Rules: cells are siblings (never nested), ids are unique per page and start from "2", parent only for shapes inside a container, no XML comments, and shapes stay within x 0 to 800 and y 0 to 600. A style used by several cells is defined once with <mxStyle name="..." value="..."/> before the cells and used by name (see the drawing guide); html=1 and whiteSpace=wrap are added automatically. To clear the canvas to one blank page, send only the two root cells <mxCell id="0"/><mxCell id="1" parent="0"/>; the previous diagram stays in History.load_diagramLoad a .drawio diagram into the current session, REPLACING the entire diagram (all pages). To change an existing file, load it here, edit with edit_diagram, then export_diagram to the same path; never rewrite the file by hand. Provide ONE of two mutually exclusive sources: 'path' (the server reads the file from disk — you do NOT need to read the file yourself or pass its XML through create_new_diagram) or 'xml' (the raw file content you already have — from another tool, a repository read, or an API response — so no temporary file needs to be written first). Both accept plain XML and draw.io's compressed save format. .drawio.svg (Editable SVG, the format export_diagram writes) is accepted too; .png files (also draw.io's editable PNG) and plain .svg files cannot be loaded. After loading from 'path' (or from compressed 'xml'), call get_diagram before edit_diagram — you haven't seen the file's cell IDs yet. Plain-XML 'xml' content you supplied yourself is already known and can be edited immediately.edit_diagramEdit a specific page in the current diagram by ID-based operations (update/add/delete cells). All-or-nothing: if any operation fails, nothing is applied and every failure is listed. Freshness: the server remembers the last diagram state you have seen, and rejects this call only if the user edited the diagram in the browser since then. You do NOT need to call get_diagram before every edit: a rejected call changes nothing and includes the current XML of the page, so you can rebuild your operations and retry. Call get_diagram first only when you don't know the current diagram content (cell IDs, structure) — e.g. the diagram wasn't created in this conversation, or you're unsure your memory of it is accurate. Multi-page targeting: - page_id / page_name / page_index are optional; when all omitted, the FIRST page is targeted - Use list_pages to discover what pages exist Operations: - add: Add a new cell. Provide cell_id (new unique id within the page) and new_xml. One cell per operation. - update: Replace an existing cell by its id. Provide cell_id and complete new_xml. - delete: Remove a cell by its id. Only cell_id is needed. Its children and connected edges are deleted too, so give only a container's id. For add/update, new_xml is the complete mxCell (inside its <object> wrapper when it has custom data, see the drawing guide) in the compact form (a shape with x, y, w, h; an edge with source and target). No XML comments. Every " inside new_xml must be escaped as \" in the JSON. Example - Add a rectangle on the default (first) page: {"operations": [{"operation": "add", "cell_id": "rect-1", "new_xml": "<mxCell id=\"rect-1\" value=\"Hello\" style=\"rounded=1;\" x=\"100\" y=\"100\" w=\"120\" h=\"60\"/>"}]} Example - Delete a cell on the default page: {"operations": [{"operation": "delete", "cell_id": "rect-1"}]}get_diagramGet the current diagram XML (fetches latest from browser, including user's manual edits). Call this when you don't know the current diagram content (cell IDs, pages, structure) — e.g. before editing a diagram you didn't create in this conversation, or after edit_diagram was rejected because the user changed the diagram in the browser. Returns the full <mxfile> by default. If a page selector is provided, returns just that page's <mxGraphModel> embedded in a one-page <mxfile> wrapper.get_selectionReturn the cells the user has selected in the preview: their ids and labels, for edges the source and target ids, for shapes the position and size, and the page they are on. Call this when the user refers to what they selected ("this box", "these arrows", "the selected shapes"), then act on the ids with edit_diagram. Says when nothing is selected. Needs the preview tab to be open.screenshot_diagramRender the diagram in the preview and return it as a PNG image, so you can see your own result. Call this once after drawing or heavily editing a complex diagram, then fix overlaps and edges that cross shapes. Without a page selector it shows the page on screen; with one it renders that page without changing what the user sees. Needs the preview tab to be open.export_diagramExport the current diagram to a file. Supports .drawio (XML), .png, .svg, and .drawio.svg (an SVG with the diagram embedded, which draw.io and load_diagram can open again). The format is auto-detected from the file extension, or can be specified explicitly. Images get a 20 px margin; a PNG has a white background (or the page's own background color) unless transparent is true. Multi-page behaviour: - .drawio with NO page selector: writes the full <mxfile> (all pages). - .drawio with a page selector: writes a single-page <mxfile> containing only that page. - .png / .svg with NO page selector: exports the currently active page in the browser. - .png with a page selector: renders that page without changing what the user sees. - .svg / .drawio.svg with a page selector: temporarily loads that page into the browser, captures it, then restores the full document (the user sees a brief flicker).list_pagesList every page (tab) in the current diagram. Returns each page's id, name, 0-based index, and cell count. Use this to discover what pages exist before targeting one with edit_diagram, get_diagram, export_diagram, rename_page, or delete_page.- +4 more on the listing page
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.
Evidence
{
"mcpServers": {
"evidence": {
"command": "npx",
"args": [
"-y",
"tersign"
]
}
}
}
Next AI Draw IO
{
"mcpServers": {
"next-ai-draw-io": {
"command": "npx",
"args": [
"-y",
"@next-ai-drawio/mcp-server@latest"
]
}
}
}
Frequently asked questions
Evidence is categorized under Developer Tools and uses a local stdio subprocess. Next AI Draw IO belongs to Developer Tools and uses a local stdio subprocess. Pick Evidence for developer tools work and Next AI Draw IO 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.
Evidence has no declared pricing — check the project's own site. Next AI Draw IO is bring-your-own-key: usage is billed by the API provider you supply a key for. Auth: api key required. 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 evidence and next-ai-draw-io as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Evidence has a quality signal of 63/100 (Good) with 3 views, 0 installs and 1 GitHub stars. Next AI Draw IO has 72/100 (Great) with 2 views, 0 installs and 36,373 GitHub stars.