Agentic Keychain
What this MCP does
Searches, evaluates, benchmarks, quotes, and unlocks reusable agent capabilities from a capability registry.
Tools
Input schema
{'type': 'object', 'required': ['capabilities'], 'properties': {'task': {'type': 'string', 'description': 'Plain description of the task you are about to do (at most 4000 characters).'}, 'model': {'type': 'string', 'description': 'The model you run on, e.g. claude-sonnet-5. Savings are reported only for measured models.'}, 'context': {'type': 'object', 'description': "Facts about your situation, keyed by the capability's parameter names (e.g. log_lines).", 'additionalProperties': {'type': ['string', 'number', 'integer', 'boolean']}}, 'constraints': {'type': 'object', 'properties': {'max_cost_usd': {'type': 'number', 'minimum': 0, 'description': 'The highest price in USD you accept; a capability priced above it is blocked (over_max_cost).'}, 'minimum_confidence': {'type': 'number', 'maximum': 0.999, 'minimum': 0.5, 'description': 'The lowest confidence in the measured saving you accept, from 0.5 to 0.999 (default 0.9); below it the answer is blocked (below_minimum_confidence).'}}, 'description': 'Limits you set for the answer; a capability outside them is reported as blocked, with the reason code.'}, 'capabilities': {'type': 'array', 'items': {'type': 'string', 'description': 'Capability id (ak:publisher:name or ak:publisher:name:x.y.z), ak:// URI or slug.'}, 'maxItems': 5, 'minItems': 2, 'description': 'Two to five capabilities to compare, each as an id, ak:// URI or slug.'}, 'expected_runs': {'type': 'integer', 'minimum': 1, 'description': 'How many times you expect to perform this kind of task.'}, 'baseline_cost_estimate_usd': {'type': 'number', 'description': 'What one run of this task costs you today without the capability, in USD.', 'exclusiveMinimum': 0}}}
Input schema
{'type': 'object', 'required': ['capability'], 'properties': {'model': {'type': 'string', 'description': 'The model you run on, e.g. claude-sonnet-5. Savings are reported only for measured models.'}, 'capability': {'type': 'string', 'description': 'Capability id (ak:publisher:name or ak:publisher:name:x.y.z), ak:// URI or slug.'}, 'expected_runs': {'type': 'integer', 'minimum': 1, 'description': 'How many times you expect to perform this kind of task.'}, 'baseline_cost_estimate_usd': {'type': 'number', 'description': 'What one run of this task costs you today without the capability, in USD.', 'exclusiveMinimum': 0}}}
Input schema
{'type': 'object', 'required': ['task'], 'properties': {'task': {'type': 'string', 'description': 'Plain description of the task you are about to do (at most 4000 characters).'}, 'model': {'type': 'string', 'description': 'The model you run on, e.g. claude-sonnet-5. Savings are reported only for measured models.'}, 'context': {'type': 'object', 'description': "Facts about your situation, keyed by the capability's parameter names (e.g. log_lines).", 'additionalProperties': {'type': ['string', 'number', 'integer', 'boolean']}}, 'capability': {'type': 'string', 'description': 'Capability id (ak:publisher:name or ak:publisher:name:x.y.z), ak:// URI or slug.'}, 'constraints': {'type': 'object', 'properties': {'max_cost_usd': {'type': 'number', 'minimum': 0, 'description': 'The highest price in USD you accept; a capability priced above it is blocked (over_max_cost).'}, 'minimum_confidence': {'type': 'number', 'maximum': 0.999, 'minimum': 0.5, 'description': 'The lowest confidence in the measured saving you accept, from 0.5 to 0.999 (default 0.9); below it the answer is blocked (below_minimum_confidence).'}}, 'description': 'Limits you set for the answer; a capability outside them is reported as blocked, with the reason code.'}, 'budget_policy': {'type': 'object', 'properties': {'auto_purchase': {'type': 'object', 'description': 'When your operator allows a purchase without asking first: enabled (true or false), max_price_usd, and minimum_expected_roi (expected net saving divided by the price). The answer says whether the policy would allow it; these tools never charge.'}, 'monthly_budget_usd': {'type': 'number', 'description': "Your operator's budget for this month in USD."}, 'spent_this_month_usd': {'type': 'number', 'description': 'What is already spent of that budget this month in USD (0 when left out).'}, 'human_approval_required': {'type': 'object', 'description': "above_usd: a price above this amount in USD needs your operator's approval even where auto_purchase is enabled."}, 'absolute_purchase_limit_usd': {'type': 'number', 'description': 'The highest price in USD for one purchase; a price above it is outside the policy.'}}, 'description': "Your operator's spending policy; the answer says whether a purchase fits it. Every purchase still needs human approval."}, 'expected_runs': {'type': 'integer', 'minimum': 1, 'description': 'How many times you expect to perform this kind of task.'}, 'baseline_cost_estimate_usd': {'type': 'number', 'description': 'What one run of this task costs you today without the capability, in USD.', 'exclusiveMinimum': 0}}}
Input schema
{'type': 'object', 'required': ['capability'], 'properties': {'capability': {'type': 'string', 'description': 'Capability id (ak:publisher:name or ak:publisher:name:x.y.z), ak:// URI or slug.'}}}
Input schema
{'type': 'object', 'required': ['capability'], 'properties': {'capability': {'type': 'string', 'description': 'Capability id (ak:publisher:name or ak:publisher:name:x.y.z), ak:// URI or slug.'}}}
Input schema
{'type': 'object', 'required': ['capability'], 'properties': {'capability': {'type': 'string', 'description': 'Capability id (ak:publisher:name or ak:publisher:name:x.y.z), ak:// URI or slug.'}}}
Input schema
{'type': 'object', 'required': ['capability'], 'properties': {'capability': {'type': 'string', 'description': 'Capability id (ak:publisher:name or ak:publisher:name:x.y.z), ak:// URI or slug.'}, 'evaluation_id': {'type': 'string', 'pattern': '^ev_[a-z2-7]{26}$', 'description': 'The evaluation_id from evaluate_capability, if you evaluated first.'}}, 'additionalProperties': False}
Input schema
{'type': 'object', 'required': ['capability', 'success'], 'properties': {'model': {'type': 'string', 'description': 'The model you run on, e.g. claude-sonnet-5. Savings are reported only for measured models.'}, 'success': {'type': 'boolean', 'description': 'Whether the task reached its goal.'}, 'cost_usd': {'type': 'number', 'minimum': 0, 'description': 'What the run cost you in USD.'}, 'tokens_in': {'type': 'integer', 'minimum': 0, 'description': 'Input tokens the run used.'}, 'capability': {'type': 'string', 'description': 'Capability id (ak:publisher:name or ak:publisher:name:x.y.z), ak:// URI or slug.'}, 'latency_ms': {'type': 'integer', 'minimum': 0, 'description': 'Wall-clock time of the run in milliseconds.'}, 'tokens_out': {'type': 'integer', 'minimum': 0, 'description': 'Output tokens the run used.'}, 'tool_calls': {'type': 'integer', 'minimum': 0, 'description': 'Tool calls the run made.'}, 'purchase_ref': {'type': 'string', 'pattern': '^pu_[a-z2-7]{26}$', 'description': 'The purchase_ref from unlock_capability, if you bought the capability.'}, 'evaluation_id': {'type': 'string', 'pattern': '^ev_[a-z2-7]{26}$', 'description': 'The evaluation_id from evaluate_capability, if you evaluated first.'}, 'failure_reason': {'enum': ['did_not_install', 'incompatible_environment', 'wrong_result', 'incomplete_result', 'too_slow', 'too_expensive', 'not_applicable_to_task', 'crashed', 'other'], 'type': 'string', 'description': 'Only with success false.'}, 'used_capability': {'type': 'boolean', 'description': 'Whether the capability was used in this run; false reports a run done without it.'}, 'baseline_cost_estimate_usd': {'type': 'number', 'minimum': 0, 'description': 'What one run of this task costs you without the capability, in USD.'}}, 'additionalProperties': False}
Input schema
{'type': 'object', 'required': ['task'], 'properties': {'task': {'type': 'string', 'description': 'Plain description of the task you are about to do (at most 4000 characters).'}, 'model': {'type': 'string', 'description': 'The model you run on, e.g. claude-sonnet-5. Savings are reported only for measured models.'}, 'context': {'type': 'object', 'description': "Facts about your situation, keyed by the capability's parameter names (e.g. log_lines).", 'additionalProperties': {'type': ['string', 'number', 'integer', 'boolean']}}, 'constraints': {'type': 'object', 'properties': {'max_cost_usd': {'type': 'number', 'minimum': 0, 'description': 'The highest price in USD you accept; a capability priced above it is blocked (over_max_cost).'}, 'minimum_confidence': {'type': 'number', 'maximum': 0.999, 'minimum': 0.5, 'description': 'The lowest confidence in the measured saving you accept, from 0.5 to 0.999 (default 0.9); below it the answer is blocked (below_minimum_confidence).'}}, 'description': 'Limits you set for the answer; a capability outside them is reported as blocked, with the reason code.', 'additionalProperties': False}, 'expected_runs': {'type': 'integer', 'minimum': 1, 'description': 'How many times you expect to perform this kind of task.'}, 'baseline_cost_estimate_usd': {'type': 'number', 'description': 'What one run of this task costs you today without the capability, in USD.', 'exclusiveMinimum': 0}}, 'additionalProperties': False}
Input schema
{'type': 'object', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'maximum': 50, 'minimum': 1, 'description': 'How many results to return, from 1 to 50 (default 10).'}, 'query': {'type': 'string', 'description': 'Search words (at most 500 characters).'}}}
Input schema
{'type': 'object', 'required': ['capability', 'license_key'], 'properties': {'quote_id': {'type': 'string', 'description': 'The quote_id of the quote the purchase followed, if any (links the records; never changes the price).'}, 'capability': {'type': 'string', 'description': 'Capability id (ak:publisher:name or ak:publisher:name:x.y.z), ak:// URI or slug.'}, 'license_key': {'type': 'string', 'description': 'License key from the checkout.'}, 'evaluation_id': {'type': 'string', 'pattern': '^ev_[a-z2-7]{26}$', 'description': 'The evaluation_id from evaluate_capability, if you evaluated first.'}}, 'additionalProperties': False}
Recent tool changes
Similar MCP servers
GPT55 Model Gateway
Acts as a remote model gateway exposing GPT chat, coding and review services, lightweight text utilities, and prepaid or x402-bas…
handoff — agent swarm coordination
Coordinates agent swarms through projects, teams, tasks, messaging, plans, delegated work, and verified payments.
MeshMarket
Provides an agent-to-agent marketplace for reasoning, persistent memory, media generation, code review, audits, business tools, a…
MeshMarket
Marketplace and gateway for metered agent capabilities including memory, reasoning, code review, research, media generation, busi…
DDG Agent Services
Acts as a pay-per-call gateway for agent tools including LLM routes, web and market data, Ethereum RPC, security scans, service c…
agent4.io
Manages grounded business agents, knowledge bases, skills, connected MCP tools, public shares, and structured interactive storyli…
x711 — Universal Agent Gas Station
Provides agents with web observation and interaction, search and retrieval, sandboxed computation, inter-agent communication, col…
k402
Provides agent-payable Kaspa services including blockchain data, covenant transactions, LLM and embedding calls, structured extra…