Home / Token cost / Stable Baseline

The Stable Baseline MCP server costs 35,752 tokens before the first call.

Connect Stable Baseline and its 184 tool definitions are loaded into the model's context on every request — 18% of a 200k window spent before your agent does anything.

QUICK ANSWER The Stable Baseline MCP server's tool definitions consume 35,752 tokens — 19× the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 184 tools · 35,752 tokens · 18% of 200k · 3.6% of 1M Method →

What that buys before your agent starts working.

Tool definitions are overhead: they occupy context on every request and compete with your code, documents and conversation history for the same window.

200K WINDOW 18%
1M WINDOW 3.6%

Corpus context: Stable Baseline ranks #20 of 3,213 measured MCP servers by definition cost. The median is 1,905 tokens, p90 is 7,952, and the heaviest (Fusionauth) is 183,337 — 92% of a 200k window on its own.

Where the 35,752 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 194 tokens per tool.

ToolCategoryTokens% of server
addWhiteboardElements Write 3,363 9.4%
updateImprovement Write 1,377 3.9%
updateTask Write 1,322 3.7%
createImprovement Write 1,145 3.2%
updateWhiteboardScene Write 803 2.2%
listWhiteboardStencils Read 792 2.2%
createTask Write 709 2.0%
kg_search Read 608 1.7%
insertDiagramInDocument Write 569 1.6%
insertWhiteboardImage Write 566 1.6%
insertWhiteboardDiagram Write 483 1.4%
traceImage Read 475 1.3%
duplicateWhiteboardElements Execute 455 1.3%
listAssignablePrincipals Read 441 1.2%
listImprovements Read 415 1.2%
renderDiagram Execute 399 1.1%
updateDiagramInDocument Write 363 1.0%
listArchitectureIcons Read 355 1.0%
dataToTable Read 349 1.0%
designWhiteboard Execute 338 0.9%
editDocument Write 330 0.9%
insertImageInDocument Write 325 0.9%
createPlanPhase Write 323 0.9%
updatePlanPhase Write 321 0.9%
updateUserPreferences Write 279 0.8%
startSignup Execute 265 0.7%
getDiagramImage Read 256 0.7%
createDocumentIngestSession Write 250 0.7%
getWhiteboardImage Read 245 0.7%
listTeams Read 245 0.7%
listPlans Read 244 0.7%
createTaskDependency Write 231 0.6%
inviteMember Write 230 0.6%
getDocument Read 226 0.6%
searchInfographicTemplates Read 223 0.6%
createDocumentFromUpload Write 221 0.6%
applyTaskDependencyCascade Write 220 0.6%
upsertResourcePermission Write 219 0.6%
rebuildPlatformCatalogEmbeddings Write 214 0.6%
updatePlan Write 209 0.6%
createDocument Write 207 0.6%
listDocumentVersions Read 203 0.6%
getWhiteboard Read 200 0.6%
getProjectHierarchy Read 198 0.6%
createPlan Write 193 0.5%
createWhiteboard Write 193 0.5%
findAndReplaceTextInDocument Read 187 0.5%
listDocuments Read 187 0.5%
createProject Write 187 0.5%
getFolderHierarchy Read 183 0.5%
listFolders Read 183 0.5%
updateImageInDocument Write 179 0.5%
pollSignupStatus Read 175 0.5%
previewKgScopeChange Write 174 0.5%
listTasks Read 173 0.5%
previewSubscriptionChange Write 168 0.5%
reorderDocuments Write 168 0.5%
listProjects Read 162 0.5%
getEffectivePermission Read 160 0.4%
reorderFolders Write 160 0.4%
setResourcePermissionOverride Write 157 0.4%
listTaskDependencies Read 156 0.4%
updateProject Write 156 0.4%
listResourcePermissions Read 155 0.4%
listWorkspaces Read 153 0.4%
addImprovementEvidence Write 153 0.4%
getKgScopeTree Read 147 0.4%
createOrganisation Write 147 0.4%
getDiagramInDocument Read 146 0.4%
listMembers Read 145 0.4%
listInvitations Read 144 0.4%
addImprovementActivity Write 144 0.4%
addPlanActivity Write 142 0.4%
createImprovementCategory Write 141 0.4%
updateMemberRole Write 140 0.4%
kg_evaluate_retrieval Write 138 0.4%
quoteCreditPackage Execute 134 0.4%
createTeam Write 133 0.4%
updateProfile Write 129 0.4%
getSubscription Read 127 0.4%
setKgProjectVisibility Write 126 0.4%
updateOrgSettings Write 126 0.4%
updateTaskDependency Write 126 0.4%
removeMember Destructive 125 0.3%
updateOrganisation Write 124 0.3%
cancelInvitation Destructive 123 0.3%
createImageUploadSession Write 123 0.3%
setKgWorkspaceScope Write 123 0.3%
listDiagramTypes Read 121 0.3%
setMemberActive Write 120 0.3%
updateTeam Write 120 0.3%
resendInvitation Execute 118 0.3%
listCreditPurchases Read 118 0.3%
createWorkspace Write 117 0.3%
updateOrgFeatureFlags Write 117 0.3%
addWorkspaceMember Write 116 0.3%
applySubscriptionChange Write 116 0.3%
createVegaDataUploadSession Write 114 0.3%
previewSubscriptionCancellation Destructive 113 0.3%
getDocumentIngestJob Read 112 0.3%
getImprovement Read 108 0.3%
previewTaskDependencyCascade Execute 107 0.3%
getTeam Read 107 0.3%
listInvoices Read 107 0.3%
searchTools Read 105 0.3%
updateWorkspaceMember Write 104 0.3%
deleteResourcePermission Destructive 103 0.3%
updateResourcePermission Write 103 0.3%
cancelAllKgInScope Destructive 102 0.3%
updateImprovementComment Write 101 0.3%
searchImprovements Read 100 0.3%
previewKgRebuild Write 100 0.3%
updatePlanComment Write 99 0.3%
getDiagramTypeGuide Read 98 0.3%
updateTeamWorkspaceAccess Write 97 0.3%
getOrganisation Read 96 0.3%
setKgDocumentScope Write 96 0.3%
purchaseCreditPackage Execute 95 0.3%
getWhiteboardGuide Read 95 0.3%
setKgFolderScope Write 95 0.3%
setPlanItemParent Write 95 0.3%
getCurrentPlanEntitlements Read 94 0.3%
getMember Read 94 0.3%
grantTeamWorkspaceAccess Write 94 0.3%
getCreditBalance Read 93 0.3%
updateWorkspace Write 93 0.3%
reactivateSubscription Destructive 91 0.3%
reorderPlanPhases Write 91 0.3%
acceptTaskDependencyReview Destructive 90 0.3%
getTask Read 90 0.3%
listOrganisations Read 89 0.2%
getOrgSettings Read 88 0.2%
listPaymentMethods Read 88 0.2%
reorderImprovementCategories Write 88 0.2%
getImageInDocument Read 87 0.2%
resetDocumentInBrain Destructive 86 0.2%
getCurrentUser Read 86 0.2%
getPriceForTier Read 86 0.2%
updateImprovementCategory Write 86 0.2%
getCustomerPortalLink Read 85 0.2%
cancelSubscription Destructive 83 0.2%
getProject Read 83 0.2%
addTeamMember Write 81 0.2%
kg_related_documents Write 78 0.2%
applyKgScopeChange Write 77 0.2%
updateBillingEmail Write 76 0.2%
getWorkspace Read 75 0.2%
removeWorkspaceMember Destructive 74 0.2%
cancelKgBuildBatch Destructive 73 0.2%
updateFolder Write 70 0.2%
revokeTeamWorkspaceAccess Destructive 69 0.2%
dismissTaskDependencyReview Destructive 68 0.2%
removeTeamMember Destructive 68 0.2%
getUserPreferences Read 68 0.2%
createFolder Write 68 0.2%
getCreditPackages Read 67 0.2%
triggerKgRebuild Execute 66 0.2%
deleteTeam Destructive 64 0.2%
getPlan Read 64 0.2%
kg_scope_status Read 63 0.2%
deleteVegaDataFile Destructive 62 0.2%
listWhiteboards Read 59 0.2%
deletePlan Destructive 57 0.2%
getPlanHierarchy Read 56 0.2%
getPlanPhase Read 56 0.2%
deleteImageInDocument Destructive 55 0.2%
deleteDiagramInDocument Destructive 54 0.2%
deletePlanPhase Destructive 54 0.2%
kg_list_communities Read 53 0.1%
deleteImprovementComment Destructive 52 0.1%
deletePlanComment Destructive 50 0.1%
kg_get_wiki_page Read 49 0.1%
kg_get_entity Read 48 0.1%
listImprovementCategories Read 46 0.1%
deleteTaskDependency Destructive 45 0.1%
deleteWhiteboard Destructive 45 0.1%
kg_suggest_sample_questions Write 45 0.1%
deleteImprovement Destructive 44 0.1%
kg_backlinks Write 44 0.1%
deleteFolder Destructive 43 0.1%
deleteImprovementCategory Destructive 43 0.1%
listPlanPhases Read 42 0.1%
getCdmdLanguageGuide Read 40 0.1%
deleteDocument Destructive 35 0.1%

Most agents use a handful of these tools. They pay for all 184.

A PolicyLayer grant exposes only the tools you allow — ungranted definitions are filtered out of the tool list, so they never enter the context window. Estimates below assume typical-weight tools (194 tokens each).

Grant scopeDefinition costReduction
All 184 tools (no gateway) 35,752 tokens
3 granted tools ~583 tokens −98%
5 granted tools ~972 tokens −97%
10 granted tools ~1,943 tokens −95%

Stable Baseline token-cost questions.

How many tokens does the Stable Baseline MCP server use?+

Its 184 tool definitions total 35,752 tokens — 18% of a 200k context window — measured with tiktoken o200k_base over the serialised tools/list payload. Exact counts vary slightly by client and model.

Why does Stable Baseline consume tokens before I send a message?+

MCP clients load every connected server's tool definitions — name, description, and input schema — into the model's context so it knows what it can call. That payload is charged against your context window on every request, whether or not a tool is used.

How do I reduce Stable Baseline's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Stable Baseline to only the tools you allow — ungranted definitions are filtered out of the tool list, so they never enter the context window. A grant of 3 typical tools costs roughly 583 tokens, a 98% reduction.

Does deferred tool loading fix this?+

Partially, in some clients. Claude Code defers MCP tool schemas behind a tool-search step by default, and VS Code has experimental grouping — but you still pay tokens per search and reload, and Cursor, Windsurf and Gemini CLI load definitions upfront. Reducing the exposed tool set cuts the cost in every client.

How these numbers were measured.

01
Serialisation

Each tool is serialised as a tools/list entry — name, description, input schema — from the schemas in the PolicyLayer scan database. Clients differ slightly in framing, so treat counts as close estimates.

02
Tokeniser

tiktoken o200k_base (GPT-4o/o-series). Anthropic's current tokeniser isn't published, so Claude's exact counts will differ; for English text and JSON schemas the totals are close enough to treat these as estimates.

03
Deferred loading

Some clients now defer schema loading (Claude Code's tool search; VS Code experimental grouping). You still pay per search and reload — and Cursor, Windsurf and Gemini CLI load everything upfront.

Computed 07-06-2026 from the PolicyLayer scan database over all 184 catalogued Stable Baseline tools. Counts refresh with every site build.

Expose only the tools you use — the rest never enter your context.

A PolicyLayer grant scopes Stable Baseline to the tools you actually allow. Ungranted definitions never load, and every call that does run is checked against policy first.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.