{"id":656207,"name":"GraphSheets","description":"Reads financial models kept in GraphSheets: lists them, gives an overview, finds rows, returns evaluated values, explains how a figure is worked out and runs the model's checks. Read-only; answers are immediate.","card_url":"https://mcp.graphsheets.ai/.well-known/agent-card.json","endpoint":"https://mcp.graphsheets.ai/a2a","protocol_version":"1.0","first_seen":"2026-11-19T00:00:50.714893+00:00","last_verified":"2026-11-19T00:00:50.714893+00:00","card":{"name":"GraphSheets","skills":[{"id":"list-models","name":"List models","tags":["models","list"],"examples":["{\"skill\":\"list-models\",\"arguments\":{}}"],"inputModes":["application/json"],"description":"The models this token can see: uid, title, head hash, when last changed, and the verification rung each is on. Send a data part {\"skill\": \"list-models\", \"arguments\": {…}}; the arguments are the `model_list` tool's.","outputModes":["application/json"]},{"id":"model-overview","name":"Model overview","tags":["models","overview"],"examples":["{\"skill\":\"model-overview\",\"arguments\":{\"model\":\"model_…\"}}"],"inputModes":["application/json"],"description":"The model at a glance: title, axis, scenarios, sections with node counts, ledgers, whether uncertainty is declared, the verification rung, check status per scenario and lint counts. Call this first. Send a data part {\"skill\": \"model-overview\", \"arguments\": {…}}; the arguments are the `model_overview` tool's.","outputModes":["application/json"]},{"id":"search-model","name":"Search a model","tags":["models","search"],"examples":["{\"skill\":\"search-model\",\"arguments\":{\"model\":\"model_…\",\"query\":\"revenue\"}}"],"inputModes":["application/json"],"description":"Find nodes by a word in their name, title, description, source, unit or formula, optionally restricted to a kind (input, calculated, constant, check, ledger). Returns declarations, not values. A kind with no query lists every node of that kind. Send a data part {\"skill\": \"search-model\", \"arguments\": {…}}; the arguments are the `model_search` tool's.","outputModes":["application/json"]},{"id":"read-values","name":"Read values","tags":["values","figures","forecast"],"examples":["{\"skill\":\"read-values\",\"arguments\":{\"model\":\"model_…\",\"nodes\":[\"income.revenue\"],\"scenario\":\"base\"}}"],"inputModes":["application/json"],"description":"Evaluated values for named nodes across the axis in a scenario, actuals overriding where present. Errors appear as their code (#REF, #DIV/0). A node whose title carries references (`{{fiscal.royalty_threshold}}`) has it worked out in that scenario under `titles`, as the reader sees it. Ask for the nodes you need, not the model. Send a data part {\"skill\": \"read-values\", \"arguments\": {…}}; the arguments are the `values_get` tool's.","outputModes":["application/json"]},{"id":"explain-figure","name":"Explain a figure","tags":["explain","audit","trace"],"examples":["{\"skill\":\"explain-figure\",\"arguments\":{\"model\":\"model_…\",\"node\":\"income.profit\",\"period\":\"2026-03\"}}"],"inputModes":["application/json"],"description":"Why a value is what it is: the evaluation trace behind one node in one period — its formula, each input's value and whether it came from a formula, an input, an actual override or an error. `depth` follows the trail further. Send a data part {\"skill\": \"explain-figure\", \"arguments\": {…}}; the arguments are the `explain` tool's.","outputModes":["application/json"]},{"id":"verify-model","name":"Verify a model","tags":["checks","lint","verify"],"examples":["{\"skill\":\"verify-model\",\"arguments\":{\"model\":\"model_…\",\"onlyFailing\":true}}"],"inputModes":["application/json"],"description":"Run the verification ladder on the model as it stands: validation issues, every lint finding with its rule and node, every check per scenario with its failing periods, the rung, and `connectivity` — the inputs nothing reads, the inputs with no values, the calculated rows nothing reads or shows, the ledger columns no formula reads, and the rows of reported history nothing reads — which is whether the graph runs from inputs through formulas to outputs. `severalRates` lists any IRR whose cashflows have more than one rate, with every rate and the one the row shows. A row named as the model's answer, one `risk_set` reports, one a statistic asks about and one a scoped check covers are all read or shown, so none of them is listed. The authoritative answer to 'what is wrong'. Send a data part {\"skill\": \"verify-model\", \"arguments\": {…}}; the arguments are the `verify` tool's.","outputModes":["application/json"]},{"id":"describe-publication","name":"Describe a published model","tags":["publication","inputs","price"],"examples":["{\"skill\":\"describe-publication\",\"arguments\":{\"publication\":\"https://graphsheets.ai/publications/pub_…?link=…\"}}"],"inputModes":["application/json"],"description":"What a published model offers: the inputs you may move (units, the author's bounds and figures, period by period), the published rows you are answered, the version it is pinned to and its verification rung, and what one evaluation costs you (who pays: you, the author's sponsorship, or you plus the author's fee). Free. Call it first, with the link the person was sent; quote prices from it, never from memory. The figures are the author's: say so, and that relying on them is the person's decision. Send a data part {\"skill\": \"describe-publication\", \"arguments\": {…}}; the arguments are the `publication_describe` tool's.","outputModes":["application/json"]},{"id":"evaluate-publication","name":"Evaluate a published model","tags":["publication","evaluate","figures"],"examples":["{\"skill\":\"evaluate-publication\",\"arguments\":{\"publication\":\"pub_…\",\"inputs\":{\"ops.gold_price\":2500},\"outputs\":[\"valuation.npv\"]}}"],"inputModes":["application/json"],"description":"Evaluate a published model at its pinned version: figures for its exposed inputs in (by name, from publication_describe — for an input one number for every period, a list period by period with null to keep the author's, or periods by label; for a constant one number), the published rows' figures out. Nothing is kept and no formula is shown. Charged as one evaluation to whoever the publication says: `quote: true` answers the price and runs nothing. A fee publication needs `acceptFee`, the fee in dollars the person agreed to — ask them before you pay one. Refused because the author's sponsorship is spent, ask the person before passing `payYourself: true`. Send a data part {\"skill\": \"evaluate-publication\", \"arguments\": {…}}; the arguments are the `publication_evaluate` tool's.","outputModes":["application/json"]}],"iconUrl":"https://mcp.graphsheets.ai/apple-touch-icon.png","version":"0.1.0","provider":{"url":"https://graphsheets.ai/","organization":"GraphSheets"},"description":"Reads financial models kept in GraphSheets: lists them, gives an overview, finds rows, returns evaluated values, explains how a figure is worked out and runs the model's checks. Read-only; answers are immediate.","capabilities":{"streaming":false,"extendedAgentCard":false,"pushNotifications":false},"securitySchemes":{"graphsheets":{"oauth2SecurityScheme":{"flows":{"authorizationCode":{"scopes":{"data:fetch":"Fetch market prices and company filings through GraphSheets","models:read":"Read the models you can open, and keep your own private scenarios and documents on them","models:write":"Create models and make changes, which land marked for your review"},"tokenUrl":"https://graphsheets.ai/api/v1/oauth/token","refreshUrl":"https://graphsheets.ai/api/v1/oauth/token","pkceRequired":true,"authorizationUrl":"https://graphsheets.ai/api/v1/oauth/authorize"}},"description":"OAuth 2.1 with PKCE and dynamic client registration. Ask for the token with resource=https://mcp.graphsheets.ai/mcp; the same connection serves MCP and A2A.","oauth2MetadataUrl":"https://graphsheets.ai/.well-known/oauth-authorization-server"}}},"documentationUrl":"https://graphsheets.ai/api/v1/docs#a2a","defaultInputModes":["application/json"],"defaultOutputModes":["application/json"],"supportedInterfaces":[{"url":"https://mcp.graphsheets.ai/a2a","protocolBinding":"JSONRPC","protocolVersion":"1.0"}],"securityRequirements":[{"schemes":{"graphsheets":{"list":["models:read"]}}}]},"status":"verified","publisher_domain":"graphsheets.ai","signature_status":"unsigned","signature_detail":"No card signature supplied","signature_key_url":null,"signature_checked_at":"2026-11-19T00:00:50.714893+00:00","domain_claimed_at":null,"domain_proof_checked_at":null,"source_name":"Publisher Agent Card","source_url":"https://mcp.graphsheets.ai/.well-known/agent-card.json","last_check":{"checked_at":"2026-11-19T00:00:50.714893+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"also_published_at":[],"history_urls":["https://mcp.graphsheets.ai/.well-known/agent-card.json"],"skills":[{"skill_id":"describe-publication","name":"Describe a published model","description":"What a published model offers: the inputs you may move (units, the author's bounds and figures, period by period), the published rows you are answered, the version it is pinned to and its verification rung, and what one evaluation costs you (who pays: you, the author's sponsorship, or you plus the author's fee). Free. Call it first, with the link the person was sent; quote prices from it, never from memory. The figures are the author's: say so, and that relying on them is the person's decision. Send a data part {\"skill\": \"describe-publication\", \"arguments\": {…}}; the arguments are the `publication_describe` tool's.","tags":["publication","inputs","price"],"quality_warning":false},{"skill_id":"evaluate-publication","name":"Evaluate a published model","description":"Evaluate a published model at its pinned version: figures for its exposed inputs in (by name, from publication_describe — for an input one number for every period, a list period by period with null to keep the author's, or periods by label; for a constant one number), the published rows' figures out. Nothing is kept and no formula is shown. Charged as one evaluation to whoever the publication says: `quote: true` answers the price and runs nothing. A fee publication needs `acceptFee`, the fee in dollars the person agreed to — ask them before you pay one. Refused because the author's sponsorship is spent, ask the person before passing `payYourself: true`. Send a data part {\"skill\": \"evaluate-publication\", \"arguments\": {…}}; the arguments are the `publication_evaluate` tool's.","tags":["publication","evaluate","figures"],"quality_warning":false},{"skill_id":"explain-figure","name":"Explain a figure","description":"Why a value is what it is: the evaluation trace behind one node in one period — its formula, each input's value and whether it came from a formula, an input, an actual override or an error. `depth` follows the trail further. Send a data part {\"skill\": \"explain-figure\", \"arguments\": {…}}; the arguments are the `explain` tool's.","tags":["explain","audit","trace"],"quality_warning":false},{"skill_id":"list-models","name":"List models","description":"The models this token can see: uid, title, head hash, when last changed, and the verification rung each is on. Send a data part {\"skill\": \"list-models\", \"arguments\": {…}}; the arguments are the `model_list` tool's.","tags":["models","list"],"quality_warning":false},{"skill_id":"model-overview","name":"Model overview","description":"The model at a glance: title, axis, scenarios, sections with node counts, ledgers, whether uncertainty is declared, the verification rung, check status per scenario and lint counts. Call this first. Send a data part {\"skill\": \"model-overview\", \"arguments\": {…}}; the arguments are the `model_overview` tool's.","tags":["models","overview"],"quality_warning":false},{"skill_id":"read-values","name":"Read values","description":"Evaluated values for named nodes across the axis in a scenario, actuals overriding where present. Errors appear as their code (#REF, #DIV/0). A node whose title carries references (`{{fiscal.royalty_threshold}}`) has it worked out in that scenario under `titles`, as the reader sees it. Ask for the nodes you need, not the model. Send a data part {\"skill\": \"read-values\", \"arguments\": {…}}; the arguments are the `values_get` tool's.","tags":["values","figures","forecast"],"quality_warning":false},{"skill_id":"search-model","name":"Search a model","description":"Find nodes by a word in their name, title, description, source, unit or formula, optionally restricted to a kind (input, calculated, constant, check, ledger). Returns declarations, not values. A kind with no query lists every node of that kind. Send a data part {\"skill\": \"search-model\", \"arguments\": {…}}; the arguments are the `model_search` tool's.","tags":["models","search"],"quality_warning":false},{"skill_id":"verify-model","name":"Verify a model","description":"Run the verification ladder on the model as it stands: validation issues, every lint finding with its rule and node, every check per scenario with its failing periods, the rung, and `connectivity` — the inputs nothing reads, the inputs with no values, the calculated rows nothing reads or shows, the ledger columns no formula reads, and the rows of reported history nothing reads — which is whether the graph runs from inputs through formulas to outputs. `severalRates` lists any IRR whose cashflows have more than one rate, with every rate and the one the row shows. A row named as the model's answer, one `risk_set` reports, one a statistic asks about and one a scoped check covers are all read or shown, so none of them is listed. The authoritative answer to 'what is wrong'. Send a data part {\"skill\": \"verify-model\", \"arguments\": {…}}; the arguments are the `verify` tool's.","tags":["checks","lint","verify"],"quality_warning":false}],"quality_flags":[],"check_history":{"checks":1,"passed":1},"recent_checks":[{"card_url":"https://mcp.graphsheets.ai/.well-known/agent-card.json","checked_at":"2026-11-19T00:00:50.714893+00:00","success":true,"http_status":200,"detail":"Agent Card validated"}],"endpoint_tls_check":{"checked_at":"2026-11-19T00:00:50.714893+00:00","success":true,"detail":"Valid TLS connection to advertised endpoint host; no A2A request sent"},"protocol_check":{"checked_at":"2026-11-19T00:00:50.714893+00:00","endpoint":"https://mcp.graphsheets.ai/a2a","protocol_binding":"JSONRPC","protocol_version":"1.0","state":"auth_required","http_status":401,"detail":"Endpoint requires authentication; A2A response not confirmed","request_diagnostics":{"requests":[{"path":"/a2a","allow":[],"method":"POST","status":401,"version_header":"1.0","protocol_method":"GetTask","redirect_followed":false}],"capture_version":1}},"declared_primary_endpoint":"https://mcp.graphsheets.ai/a2a","selected_connection_interface":{"url":"https://mcp.graphsheets.ai/a2a","protocolBinding":"JSONRPC","protocolVersion":"1.0"},"protocol_interface_checks":[{"endpoint":"https://mcp.graphsheets.ai/a2a","protocol_binding":"JSONRPC","protocol_version":"1.0","selected":true,"state":"auth_required","checked_at":"2026-11-19T00:00:50.714893+00:00","http_status":401,"detail":"Endpoint requires authentication; A2A response not confirmed","binding_recorded":true}],"connection_selection_note":"The selected connection uses an address advertised in the publisher card. Read-only observations do not establish task quality or safety.","x402_price_check":null,"events":[],"relationships":[],"verification":{"agent_card_url":"https://mcp.graphsheets.ai/.well-known/agent-card.json","last_successful_card_check":"2026-11-19T00:00:50.714893+00:00","latest_card_check":{"checked_at":"2026-11-19T00:00:50.714893+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"signature_status":"unsigned","signature_checked_at":"2026-11-19T00:00:50.714893+00:00","task_endpoint_tested":true,"task_execution_tested":false,"endpoint_tls_checked_at":"2026-11-19T00:00:50.714893+00:00","endpoint_tls_reachable":true,"protocol_check_state":"auth_required","protocol_checked_at":"2026-11-19T00:00:50.714893+00:00","provider_identity_verified":false,"domain_claimed_at":null,"domain_proof_checked_at":null},"synthetic_capability_tests":{"agent_id":656207,"status":"not_tested","reason_code":"not_yet_tested","consent_status":"not_confirmed","latest_observation_status":null,"last_checked_at":null,"fixture_version":"1","reference_demonstration":false,"scope":"A publisher-authorized synthetic test of a dedicated free test endpoint. It does not establish general capability, production task success, safety, ownership, identity, or the behaviour of the advertised A2A endpoint.","methodology_url":"https://localmark.ai/capability-tests","history":[]},"repair_links":{"agent_repair_url":"https://localmark.ai/agents/656207/repair","publisher_report_url":"https://localmark.ai/publishers/graphsheets.ai/repair","diagnostics_json_url":"https://localmark.ai/publishers/graphsheets.ai/repair/diagnostics.json","diagnostics_csv_url":"https://localmark.ai/publishers/graphsheets.ai/repair/diagnostics.csv"},"_localmark":{"contribution":{"optional":true,"directory_access":"free","operator_authorization_required":true,"affects_rankings":false,"message":"LocalMark is free. Optional contributions help fund ongoing checks.","support_url":"https://localmark.ai/support","metadata_url":"https://localmark.ai/api/v1/support/contributions"}}}