XGR MCP Gateway
REMOTE · MCP.XGR.NETWORK
Public Streamable HTTP MCP gateway for XGRChain, XDaLa sessions, Explorer data and XGR standards.
Available components
Last scanned (11 hours ago)
Scores higher than 89% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Crypto and Web3
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security74
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability74
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 12395 tokens (~110/item across 112 items; 112 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety90
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 3 of 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "get_xdala_bundle_deploy_handoff" implies "deploy" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
- An AI judge read all 112 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 24 Oct 26 0
- Schema quality: 10617 → 12395 ▼ functional
- Destructive annotations: 50% → 60% ▲ functional
- Schema quality: excellent → good functional
- New tool “agent_commons_ask_peers” functional
- New tool “agent_commons_discover” functional
- New tool “agent_commons_inbox” functional
- New tool “agent_commons_list_topics” functional
- New tool “agent_commons_live_file” functional
- New tool “agent_commons_live_join” functional
- New tool “agent_commons_live_post” functional
- New tool “agent_commons_live_read” functional
- New tool “agent_commons_live_wait” functional
- New tool “agent_commons_mark_read” functional
- New tool “agent_commons_message_file” functional
- New tool “agent_commons_post” functional
- New tool “agent_commons_read_topic” functional
- New tool “agent_commons_register” functional
- New tool “get_xgr_public_readkey” functional
- New tool “list_xgr_grants” functional
- New tool “list_xgr_grants_for_readkey” functional
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Aug 26 0
- Stability: 0.97 → pass security
- 17 Aug 26 0
- New tool “search_xgr_transactions” functional
- 16 Aug 26 0
- Tool “create_xgr_purchase_order” rewrote its description, which is the text the model reads security
- Tool “create_xgr_purchase_order_by_budget” rewrote its description, which is the text the model reads security
- Tool “get_xgr_purchase_options” rewrote its description, which is the text the model reads security
- Tool “quote_xgr_purchase” rewrote its description, which is the text the model reads security
- Schema quality: 8922 → 10387 ▼ functional
- Schema quality: good → excellent functional
- New tool “expand_address_relation_graph” functional
- New tool “get_address_relation_graph” functional
- New tool “get_relation_edge_transactions” functional
- New tool “get_xdala_start_payload_history” functional
- New tool “trace_xgr_transaction” functional
- New tool “trace_xgr_value_flow” functional
- “create_xdala_session_start_handoff” reworded the description of “bundleDeployHandle” cosmetic
- “create_xgr_purchase_order” reworded the description of “amount_xgr” cosmetic
- “create_xgr_purchase_order” reworded the description of “country_code” cosmetic
- “create_xgr_purchase_order” reworded the description of “email” cosmetic
- “create_xgr_purchase_order” reworded the description of “name” cosmetic
- “create_xgr_purchase_order” reworded the description of “payment_asset” cosmetic
- “create_xgr_purchase_order” reworded the description of “sender_wallet” cosmetic
- “create_xgr_purchase_order” reworded the description of “terms_accepted” cosmetic
- “create_xgr_purchase_order” reworded the description of “xgr_wallet” cosmetic
- “create_xgr_purchase_order_by_budget” reworded the description of “country_code” cosmetic
- “create_xgr_purchase_order_by_budget” reworded the description of “email” cosmetic
- “create_xgr_purchase_order_by_budget” reworded the description of “max_payment_amount” cosmetic
- “create_xgr_purchase_order_by_budget” reworded the description of “name” cosmetic
- “create_xgr_purchase_order_by_budget” reworded the description of “payment_asset” cosmetic
- “create_xgr_purchase_order_by_budget” reworded the description of “safety_margin_bps” cosmetic
- “create_xgr_purchase_order_by_budget” reworded the description of “sender_wallet” cosmetic
- “create_xgr_purchase_order_by_budget” reworded the description of “terms_accepted” cosmetic
- “create_xgr_purchase_order_by_budget” reworded the description of “xgr_wallet” cosmetic
- “quote_xgr_purchase” reworded the description of “max_payment_amount” cosmetic
- “quote_xgr_purchase” reworded the description of “payment_asset” cosmetic
- “quote_xgr_purchase” reworded the description of “safety_margin_bps” cosmetic
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://mcp.xgr.network/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=mcp.xgr.network | CN=YE2,O=Let's Encrypt,C=US | 5 Oct 2026 | 3 Jan 2027 | ECDSA 256 | ECDSA-SHA384 | 602566917c9607fa9a5881ae1fcbcd72dc4 |
| SANs: mcp.xgr.network | ||||||
| CN=YE2,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 4df3b15dd6c0784c507cd37b58e6f115 |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of mcp.xgr.network. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| network. | DS published | 11416, 40414 | 8, 8 | Verified |
| xgr.network. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mcp.xgr.network/mcp | Verified | 200 | |
| http (plaintext) | http://mcp.xgr.network/mcp | HTTPS enforced | 301 | https://mcp.xgr.network/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
resolve_xrc729_process_graph Resolve XRC-729 process graph ~104
Resolve deployed XRC-729 OSTC runtime JSON and linked indexed XRC-137 rule contracts without mutating chain state.
| Name | Type | Req | Description |
|---|---|---|---|
| includeRules | boolean | – | Value for the include rules parameter. |
| includeUsage | boolean | – | Value for the include usage parameter. |
| ostcId | string | – | Orchestration step contract id for the XDaLa workflow. |
| xrc729Address | string | yes | Value for the xrc729 address parameter. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | – | yes | Structured result data returned by the XGR MCP gateway. |
No examples provided.
search_transactions Search transactions ~321
Read-only chain-wide Explorer DB transaction search. Use for general transaction, native XGR value, from/to address, hash, input, session id, validity/execution, and block/time-range questions; do not sample XDaLa sessions for chain-wide transaction questions.
| Name | Type | Req | Description |
|---|---|---|---|
| contractCreation | boolean | – | Value for the contract creation parameter. |
| executed | boolean | – | Value for the executed parameter. |
| from | string | – | Sender address or lower bound used for the query. |
| fromBlock | integer | – | Value for the from block parameter. |
| hasInput | boolean | – | Value for the has input parameter. |
| hasValue | boolean | – | Value for the has value parameter. |
| limit | integer | – | Maximum number of records to return. |
| page | integer | – | One-based page number for paginated explorer/API results. |
| sessionId | string | – | XDaLa session identifier used to query runtime or explorer data. |
| to | string | – | Recipient address, contract address or upper bound used for the query. |
| toBlock | integer | – | Value for the to block parameter. |
| txHash | string | – | 0x-prefixed transaction hash to inspect or resolve. |
| valid | boolean | – | Value for the valid parameter. |
| valueEqWei | string | – | Value for the value eq wei parameter. |
| valueGtWei | string | – | Value for the value gt wei parameter. |
| valueLtWei | string | – | Value for the value lt wei parameter. |
| windowHours | integer | – | Value for the window hours parameter. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | – | yes | Structured result data returned by the XGR MCP gateway. |
No examples provided.
search_xgr_transactions Search native XGR transactions for flow analysis ~230
Find indexed native-XGR transactions using time, value and address filters before choosing a transaction for Relation Graph or Value Flow analysis. Typical use: all native transfers in the last 24 hours above a given XGR/wei amount. Results are read-only and cursor-paginated for latest/oldest sorting.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | – | Optional address that may appear on either side of the transfer. |
| cursor | string | – | Cursor returned by a previous latest/oldest search. |
| fromAddress | string | – | Optional exact sender address. |
| fromTimestamp | integer | – | Optional inclusive Unix-seconds lower time bound. |
| limit | integer | – | Maximum number of records to return. |
| maxValueWei | string | – | Optional maximum native XGR transfer value in wei. |
| minValueWei | string | – | Minimum native XGR transfer value in wei. |
| sort | string | – | Sort order. largest is intentionally a bounded single-page picker view. |
| toAddress | string | – | Optional exact recipient address. |
| toTimestamp | integer | – | Optional inclusive Unix-seconds upper time bound. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | – | yes | Structured result data returned by the XGR MCP gateway. |
No examples provided.
trace_xgr_transaction Trace an XGR transaction relation graph ~177
Loads an indexed transaction, uses its sender as the bounded graph root, returns sender/recipient trace roots plus the graph and an explicit edge to highlight. Useful for following native XGR transaction relations, but it does not attribute later mixed balances to the seed value.
| Name | Type | Req | Description |
|---|---|---|---|
| depth | integer | – | Value for the depth parameter. |
| direction | string | – | Value for the direction parameter. |
| fromTimestamp | integer | – | Value for the from timestamp parameter. |
| maxEdges | integer | – | Value for the max edges parameter. |
| maxNodes | integer | – | Value for the max nodes parameter. |
| minValueWei | string | – | Value for the min value wei parameter. |
| toTimestamp | integer | – | Value for the to timestamp parameter. |
| txHash | string | yes | 0x-prefixed transaction hash to inspect or resolve. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | – | yes | Structured result data returned by the XGR MCP gateway. |
No examples provided.
trace_xgr_value_flow Trace native XGR value provenance ~238
Read-only native-XGR value-flow analysis starting from one transaction. Use model="possible" for conservative attribution ranges or model="proportional" for haircut attribution. Native XGR has no per-coin identity, so results are provenance models rather than proof that a specific coin moved. maxTransfers and maxHops accept a number or "all"; "all" is still bounded by Explorer server safety caps and reports truncation explicitly.
| Name | Type | Req | Description |
|---|---|---|---|
| amountWei | string | – | Optional amount of the seed transaction value to trace in wei. Defaults to the full native XGR value of the seed transaction. |
| maxHops | – | – | Maximum propagation hops from the seed recipient, or "all" subject to server safety caps. |
| maxTransfers | – | – | Maximum propagated transfers to return, or "all" to continue until exhaustion subject to server safety caps. |
| minAttributedWei | string | – | Ignore branches whose possible/attributed amount falls below this wei threshold. |
| model | string | – | possible returns attribution ranges; proportional applies a haircut/share model. |
| txHash | string | yes | 0x-prefixed transaction hash to inspect or resolve. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | – | yes | Structured result data returned by the XGR MCP gateway. |
No examples provided.
validate_xdala_blueprint Validate XDaLa blueprint ~95
Validate XRC-729 OSTC plus per-step XRC-137 payload-flow consistency.
| Name | Type | Req | Description |
|---|---|---|---|
| entryStepId | string | yes | Value for the entry step id parameter. |
| initialPayloadFields | array | – | Value for the initial payload fields parameter. |
| ostc | object | yes | Value for the ostc parameter. |
| xrc137ByStep | object | yes | Value for the xrc137 by step parameter. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | – | yes | Structured result data returned by the XGR MCP gateway. |
No examples provided.
validate_xdala_bundle Validate XDaLa bundle ~41
Alias for validate_xgr_multibundle.
| Name | Type | Req | Description |
|---|---|---|---|
| bundle | object | yes | Canonical XDaLa bundle JSON object to validate, store or hand off. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | – | yes | Structured result data returned by the XGR MCP gateway. |
No examples provided.
validate_xdala_rules Validate XDaLa rule expressions ~44
Validate rule expressions against available placeholder fields.
| Name | Type | Req | Description |
|---|---|---|---|
| availableFields | array | – | Value for the available fields parameter. |
| rules | array | yes | Value for the rules parameter. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | – | yes | Structured result data returned by the XGR MCP gateway. |
No examples provided.
validate_xgr_multibundle Validate XGR MultiBundle ~47
Validate canonical deployable xgr-multi-bundle@1.
| Name | Type | Req | Description |
|---|---|---|---|
| bundle | object | yes | Canonical XDaLa bundle JSON object to validate, store or hand off. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | – | yes | Structured result data returned by the XGR MCP gateway. |
No examples provided.
validate_xgr_session_start Validate legacy XGR Session Start ~34
Validate legacy low-level session-start payload only.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionStart | object | yes | Value for the session start parameter. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | – | yes | Structured result data returned by the XGR MCP gateway. |
No examples provided.
validate_xgr_session_start_handoff Validate XGR Session Start Handoff ~46
Validate a canonical Workbench xgr-session-start@1 request.
| Name | Type | Req | Description |
|---|---|---|---|
| request | object | yes | Canonical request object used by the target XDaLa workflow operation. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | – | yes | Structured result data returned by the XGR MCP gateway. |
No examples provided.
validate_xrc137_authoring Validate XRC-137 authoring rules ~35
Validate a drafted XRC-137 authoring object.
| Name | Type | Req | Description |
|---|---|---|---|
| rule | object | yes | Value for the rule parameter. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | – | yes | Structured result data returned by the XGR MCP gateway. |
No examples provided.
How do I install the XGR MCP Gateway server?
XGR MCP Gateway is a hosted endpoint at https://mcp.xgr.network/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · mcp.xgr.network
claude mcp add --transport http xgr-network-xdala-workflow-builder 'https://mcp.xgr.network/mcp'
What is the XGR MCP Gateway server?
XGR MCP Gateway is listed in the public MCP registry as io.github.xgr-network/xdala-workflow-builder. Public Streamable HTTP MCP gateway for XGRChain, XDaLa sessions, Explorer data and XGR standards. This page covers its hosted endpoint (https://mcp.xgr.network/mcp).
Is the XGR MCP Gateway server safe to use?
XGR MCP Gateway scores 84 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the XGR MCP Gateway server expose?
XGR MCP Gateway exposes 112 tools: get_xgr_network_info, get_chain_status, get_latest_block, get_account_live_state, get_transaction_evidence, and 107 more. Their descriptions and schemas cost roughly 12,395 tokens of context every time the server is loaded.
Does the XGR MCP Gateway server require authentication?
No. We connected to XGR MCP Gateway without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the XGR MCP Gateway server still maintained?
XGR MCP Gateway is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the XGR MCP Gateway server?
VerifyMCP ran 13 checks on XGR MCP Gateway, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.