Topology Index

by com.topologyindex

Overview Discussions Admin

Server Details

Reference for multi-agent LLM topologies: patterns, aliases, sources, starters; one gated report.

Ownership verified

Status: Healthy
Uptime: 100.0% over 34 days
Last Tested: 2026-11-02 19:02
Transport: Streamable HTTP · MCP 2025-11-25
URL

TDQS

A3.9/5.0

Scored 2026-10-29 05:20 across 6 tools

Disambiguation4/5

The core split is clear: `search` (keyword lookup), `list_patterns`/`list_starters` (browse indexes), `get_pattern` (single pattern detail), `fetch` (arbitrary page), `report_outcome` (feedback loop). The one real overlap is `fetch` versus `get_pattern`, since `fetch` can also retrieve /patterns/{pattern}.md; the descriptions mitigate this by explaining that `get_pattern` adds aliases, failure modes, execution eligibility and a redemption ticket, but an agent could still reach for `fetch` and lose the ticket flow.

Naming Consistency3/5

Four tools follow verb_noun (`get_pattern`, `list_patterns`, `list_starters`, `report_outcome`) while two are bare verbs (`fetch`, `search`). The pattern is readable and the bare verbs are conventional for generic retrieval, but the set is not uniformly predictable.

Tool Count5/5

Six tools is tight and well-scoped for a content index: retrieval, browsing, detail lookup, keyword search and an outcome-reporting loop. Each tool has a distinct role and nothing looks like filler or a versioned duplicate.

Completeness4/5

Coverage is good: browse indexes, single-item reads, free-form page fetch, search, and a feedback mechanism with verification follow-ups. Minor gaps exist — there is no dedicated domain or findings index tool (domains are reachable only as an argument to `list_patterns` or via `fetch`), and research/guide/benchmark listings depend on `search` or knowing the path.

Available Tools

6 tools

fetchFetch a public pageA

Read-onlyIdempotent

Inspect

Returns the Markdown document of any public page, exactly as HTTP serves it, from a root-relative path (/patterns/supervisor.md) or a https://topologyindex.com URL. Private tenant routes are not reachable here. A pattern, starter or formation read may add a second item containing a one-time use ticket and an instruction to call report_outcome after applying it; a pattern or starter redemption returns a verification checklist, or the pattern to test next when it did not work.

Name	Required	Description	Default
`path_or_url`	Yes	A path such as /patterns/index.md, or https://topologyindex.com/patterns/index.md.

TDQS

A3.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, yet the description adds real substance: what is unreachable (private tenant routes), that a read may emit a second item with a one-time-use ticket, and that report_outcome should then be called. It omits how a caller should handle a failed/404 fetch, but the added side-effect context is well beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The main purpose is front-loaded in the first sentence and every clause carries information. The second sentence is dense and stacks several distinct behaviors (ticket item, report_outcome, checklist) into one run-on, which slightly hurts scannability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must carry return-value burden, and it does: Markdown document, possible second item with a ticket, and either a verification checklist or the next pattern to test. Given a single well-documented parameter and full annotation coverage, this is nearly complete, though the shape of error responses is unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single parameter is fully documented in the schema, so the baseline is 3. The description's path/URL examples ('/patterns/supervisor.md') duplicate what the schema already provides and add no new syntax or validation meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Returns the Markdown document of any public page, exactly as HTTP serves it') plus the accepted input forms. It implicitly distinguishes itself from get_pattern by emphasizing raw-as-served content, but never names or contrasts with the sibling tools, so an agent must infer which of fetch vs get_pattern to prefer.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The exclusion 'Private tenant routes are not reachable here' is an explicit when-not, and the notes about pattern/starter reads imply when the ticket/checklist behavior applies. However, there is no statement of when to choose fetch over get_pattern, list_patterns, or search, so the routing decision is left implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_patternGet a patternA

Read-onlyIdempotent

Inspect

One pattern page (/patterns/{pattern}.md): definition, aliases, when it is hypothesised to fit, failure modes, sources and whether this deployment can execute it. Accepts a pattern identifier or a known alias. Adds a second item with a one-time use ticket and a one-line instruction when this selected read is eligible; report_outcome returns useful indexed follow-up after redemption.

Name	Required	Description	Default
`pattern`	Yes	A pattern identifier such as supervisor, or an alias such as orchestrator-worker.

TDQS

A3.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral content beyond that: a conditional second output item carrying a one-time use ticket and a one-line instruction, plus the follow-up flow via report_outcome after redemption.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with what is returned, then the input form, then the conditional ticket behavior. Dense but purposeful; the semicolon-chained second sentence is slightly harder to parse than it needs to be, but no sentence is pure filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With one param, no output schema, and a non-obvious side effect, the description must carry the return shape and it does enumerate the page contents plus the conditional ticket item. It could be slightly clearer about the ticket's purpose and how report_outcome consumes it, but nothing essential for calling the tool is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single param is already fully described in the schema ('A pattern identifier such as supervisor, or an alias such as orchestrator-worker'). The description's 'Accepts a pattern identifier or a known alias' largely restates the schema rather than adding format, resolution, or error semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('One pattern page') and enumerates the page's contents (definition, aliases, fit hypotheses, failure modes, sources, executability). It is clearly distinct from list_patterns and search, though it never explicitly separates itself from the sibling `fetch`, which could also retrieve a page.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: an agent can infer this is a single-item lookup by identifier or alias versus listing/searching. There is no explicit 'use this when...' guidance, and no statement of when to prefer report_outcome or fetch instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_patternsList patternsB

Read-onlyIdempotent

Inspect

The decision guide: where to start by the shape of the task, the pattern to consider next and when to avoid each, plus the pattern families (the choosing rows of /patterns/index.md, without the rest of that page). With a family, /patterns/index.md?family={family}: that family’s patterns and the rows that name them. With a domain, /domains/{domain}.md: the task shapes common in that kind of work, their rows, the sources of the published findings tagged with it (never a ranking; each finding in words at /domains/{domain}/findings.md) and its starters. The response includes exact next calls for the listed patterns and starters.

Name	Required	Description	Default
`domain`	No	Read the lens of one task domain instead; not together with a family.
`family`	No	Restrict the list to one pattern family.

Output Schema

Name	Required	Description
`next`	Yes

TDQS

B3.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, not open-world), and the description still adds real context: the domain findings are 'never a ranking,' findings are rendered 'in words,' and the response embeds exact next calls. That is meaningful behavior beyond the annotations, though it omits any pagination/size caveats.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One long, colon-chained sentence-fragment block that mixes purpose, file paths, query-string syntax and return contents. It is information-dense but not front-loaded or skimmable; much of the path plumbing (/patterns/index.md?family={family}) crowds out the essential message.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be explained, and the description still covers both optional parameters and the downstream routing. For a 2-param read-only listing tool this is nearly sufficient; only the missing sibling differentiation keeps it from being complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with both enums described, so baseline is 3. The description goes further by mapping each parameter choice to what it retrieves (a family yields that family's patterns and naming rows; a domain yields task shapes, tagged sources and starters), adding semantic value over the schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description frames the tool as a "decision guide" that returns pattern families, task shapes and next-step pointers, and it varies its output by the family/domain argument. However, it never states a clean verb+resource (e.g. "lists available patterns"), instead burying the purpose in path-level detail, so an agent must infer what is actually returned.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explains what happens 'with a family' and 'with a domain,' which implies when to pass each, and it promises exact next calls, implicitly routing to get_pattern/fetch. But it never states when to prefer this over siblings like search, fetch, or list_starters, so comparison guidance is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_startersList starter formationsA

Read-onlyIdempotent

Inspect

The starter formation index (/starters/index.md): unvalidated, unsigned FORMATION.md documents to copy and register privately. With a task class, only the starters that declare it (/starters/index.md?task_class={task_class}). The response includes exact fetch calls for the starter paths.

Name	Required	Description	Default
`task_class`	No	A task class such as coding.bugfix.

Output Schema

Name	Required	Description
`next`	Yes

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish readOnly/idempotent/non-destructive/openWorld=false, so the description earns credit for added trust context: documents are 'unvalidated, unsigned' and must be registered privately. It also discloses that the response includes exact fetch calls, which is behavior beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Compact, front-loaded with the resource identity, then the filter behavior, then the response shape. The inline URL syntax is slightly dense but earns its place by showing the exact index path.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values needn't be detailed, and the description covers identity, trust caveat, filtering, and response shape. Nothing critical to calling it correctly appears missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the param is optional, so baseline would be 3, but the description adds filter semantics the schema lacks: supplying a task_class narrows results to starters that declare it, and it even sketches the query form.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (the starter formation index of FORMATION.md documents) and what the tool returns. It reads clearly as a listing tool distinct from list_patterns/get_pattern by operating on 'starters/formations' rather than patterns, though it never names the sibling it displaces.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'to copy and register privately' phrasing implies the use case, and it explains the task_class filter condition, but there is no explicit when-to-use-this-vs-list_patterns guidance or stated prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

report_outcomeReport a use ticket outcomeA

Idempotent

Inspect

Limited rollout: only for a use ticket from a pattern, starter or formation read. If you have no ticket, do not call it. With one, report once after applying it when you know the outcome: worked, partly or did_not_work, with an optional short note. The response returns a useful follow-up from indexed content when one exists. No account or API key is needed. No prompt, code or log is stored. Terms: /docs/api/contributing.md.

Name	Required	Description	Default
`note`	No
`ticket`	Yes
`outcome`	Yes

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations: discloses no account or API key required, that no prompt/code/log is stored, and that the response may return a follow-up from indexed content. Adds privacy and auth context that readOnlyHint/idempotentHint alone cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The eligibility constraint is front-loaded, followed by when to call, the payload, and the response behavior. Every sentence carries information; the terms link is a minor but reasonable trailing addition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-param tool with no output schema, the description covers eligibility, timing, payload values, privacy, and a loose description of the return ('useful follow-up from indexed content when one exists'). The return shape is only characterized qualitatively, a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description compensates by explaining all three params: the source of 'ticket', the three 'outcome' values verbatim, and that 'note' is optional and short. It does not mention the 280-char limit, which remains discoverable only in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (report) and resource (a use ticket outcome), plus the exact accepted values. The gating sentence about tickets from a pattern, starter, or formation read separates it clearly from the read-only siblings (fetch, get_pattern, list_patterns, list_starters, search).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use and when-not: 'only for a use ticket from a pattern, starter or formation read' and 'If you have no ticket, do not call it.' It also specifies timing ('report once after applying it when you know the outcome'), leaving nothing to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

searchSearch Topology IndexA

Read-onlyIdempotent

Inspect

Keyword search, with common synonyms, over pattern names, aliases and families, the decision guide, the domains, sources and benchmarks of published findings, research, starters and guides. At most 10 results, each a path for fetch; canonical pattern results also include the identifier for get_pattern and an exact next call. If no page matches every word, pages matching some; if none, the decision guide. Matches text only; never ranks patterns.

Name	Required	Description	Default
`query`	No	Words to look for, such as "orchestrator worker", "verification" or "coding". Only the first 200 characters are searched.

Output Schema

Name	Required	Description
`next`	No
`match`	Yes
`results`	Yes

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well past the readOnly/idempotent annotations by disclosing fallback behavior (all-words match, then partial match, then decision guide), the 10-result cap, and the semantic limit that it matches text only and never ranks patterns. These are behavioral traits an agent cannot infer from the annotations or schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then result shape, then fallback semantics; nearly every clause carries information. The middle sentence is densely packed with multiple ideas, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter search with an output schema and full annotation coverage, the description supplies everything additional an agent needs: scope of the index, synonym behavior, result cap, result-to-next-tool mapping, and degradation order. Nothing material is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (including the 200-character search window), so the baseline is 3. The description adds real value by disclosing synonym expansion, which directly changes how an agent should phrase the query.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (keyword search with synonym expansion) and enumerates the resource surfaces searched: pattern names, aliases, families, decision guide, domains, sources, benchmarks, research, starters, guides. This makes it clearly distinct from fetch, get_pattern, and list_patterns, which the description references by name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent: each result is a path for `fetch`, canonical pattern results carry the identifier for `get_pattern` plus an exact next call. That is strong forward guidance, but it never states when NOT to use this tool (e.g., when to prefer list_patterns for browsing), so it sits just below the top mark.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

1 tool updateNov 2, 2026

Changedsearch5 fields changed

removedInput schema / additionalProperties
```
Removed value: -false
```

changedInput schema / properties / query / description

Previous value: -"Words to look for, such as \"orchestrator worker\", \"verification\" or \"coding\"."New value: +"Words to look for, such as \"orchestrator worker\", \"verification\" or \"coding\". Only the first 200 characters are searched."

changedInput schema / properties / query / maxLength
```
Previous value: -200New value: +4096
```
removedInput schema / properties / query / minLength
```
Removed value: -1
```
removedInput schema / required
```
Removed value: -[
-  "query"
-]
```

3 tool updatesOct 2, 2026

Changedlist_patterns1 field changed

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "next": {
+      "items": {
+        "oneOf": [
+          {
+            "additionalProperties": false,
+            "properties": {
+              "arguments": {
+                "additionalProperties": false,
+                "properties": {
+                  "path_or_url": {
+                    "maxLength": 2048,
+                    "minLength": 1,
+                    "type": "string"
+                  }
+                },
+                "required": [
+                  "path_or_url"
+                ],
+                "type": "object"
+              },
+              "tool": {
+                "const": "fetch",
+                "type": "string"
+              }
+            },
+            "required": [
+              "tool",
+              "arguments"
+            ],
+            "type": "object"
+          },
+          {
+            "additionalProperties": false,
+            "properties": {
+              "arguments": {
+                "additionalProperties": false,
+                "properties": {
+                  "pattern": {
+                    "maxLength": 64,
+                    "minLength": 1,
+                    "type": "string"
+                  }
+                },
+                "required": [
+                  "pattern"
+                ],
+                "type": "object"
+              },
+              "tool": {
+                "const": "get_pattern",
+                "type": "string"
+              }
+            },
+            "required": [
+              "tool",
+              "arguments"
+            ],
+            "type": "object"
+          },
+          {
+            "additionalProperties": false,
+            "properties": {
+              "arguments": {
+                "additionalProperties": false,
+                "properties": {},
+                "type": "object"
+              },
+              "tool": {
+                "const": "list_patterns",
+                "type": "string"
+              }
+            },
+            "required": [
+              "tool",
+              "arguments"
+            ],
+            "type": "object"
+          }
+        ]
+      },
+      "maxItems": 32,
+      "type": "array"
+    }
+  },
+  "required": [
+    "next"
+  ],
+  "type": "object"
+}

Changedlist_starters1 field changed

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "next": {
+      "items": {
+        "oneOf": [
+          {
+            "additionalProperties": false,
+            "properties": {
+              "arguments": {
+                "additionalProperties": false,
+                "properties": {
+                  "path_or_url": {
+                    "maxLength": 2048,
+                    "minLength": 1,
+                    "type": "string"
+                  }
+                },
+                "required": [
+                  "path_or_url"
+                ],
+                "type": "object"
+              },
+              "tool": {
+                "const": "fetch",
+                "type": "string"
+              }
+            },
+            "required": [
+              "tool",
+              "arguments"
+            ],
+            "type": "object"
+          },
+          {
+            "additionalProperties": false,
+            "properties": {
+              "arguments": {
+                "additionalProperties": false,
+                "properties": {
+                  "pattern": {
+                    "maxLength": 64,
+                    "minLength": 1,
+                    "type": "string"
+                  }
+                },
+                "required": [
+                  "pattern"
+                ],
+                "type": "object"
+              },
+              "tool": {
+                "const": "get_pattern",
+                "type": "string"
+              }
+            },
+            "required": [
+              "tool",
+              "arguments"
+            ],
+            "type": "object"
+          },
+          {
+            "additionalProperties": false,
+            "properties": {
+              "arguments": {
+                "additionalProperties": false,
+                "properties": {},
+                "type": "object"
+              },
+              "tool": {
+                "const": "list_patterns",
+                "type": "string"
+              }
+            },
+            "required": [
+              "tool",
+              "arguments"
+            ],
+            "type": "object"
+          }
+        ]
+      },
+      "maxItems": 32,
+      "type": "array"
+    }
+  },
+  "required": [
+    "next"
+  ],
+  "type": "object"
+}

Changedsearch4 fields changed

addedOutput schema / properties / next

Added value: +{
+  "oneOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "arguments": {
+          "additionalProperties": false,
+          "properties": {
+            "path_or_url": {
+              "maxLength": 2048,
+              "minLength": 1,
+              "type": "string"
+            }
+          },
+          "required": [
+            "path_or_url"
+          ],
+          "type": "object"
+        },
+        "tool": {
+          "const": "fetch",
+          "type": "string"
+        }
+      },
+      "required": [
+        "tool",
+        "arguments"
+      ],
+      "type": "object"
+    },
+    {
+      "additionalProperties": false,
+      "properties": {
+        "arguments": {
+          "additionalProperties": false,
+          "properties": {
+            "pattern": {
+              "maxLength": 64,
+              "minLength": 1,
+              "type": "string"
+            }
+          },
+          "required": [
+            "pattern"
+          ],
+          "type": "object"
+        },
+        "tool": {
+          "const": "get_pattern",
+          "type": "string"
+        }
+      },
+      "required": [
+        "tool",
+        "arguments"
+      ],
+      "type": "object"
+    },
+    {
+      "additionalProperties": false,
+      "properties": {
+        "arguments": {
+          "additionalProperties": false,
+          "properties": {},
+          "type": "object"
+        },
+        "tool": {
+          "const": "list_patterns",
+          "type": "string"
+        }
+      },
+      "required": [
+        "tool",
+        "arguments"
+      ],
+      "type": "object"
+    }
+  ]
+}

addedOutput schema / properties / results / items / properties / next

Added value: +{
+  "oneOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "arguments": {
+          "additionalProperties": false,
+          "properties": {
+            "path_or_url": {
+              "maxLength": 2048,
+              "minLength": 1,
+              "type": "string"
+            }
+          },
+          "required": [
+            "path_or_url"
+          ],
+          "type": "object"
+        },
+        "tool": {
+          "const": "fetch",
+          "type": "string"
+        }
+      },
+      "required": [
+        "tool",
+        "arguments"
+      ],
+      "type": "object"
+    },
+    {
+      "additionalProperties": false,
+      "properties": {
+        "arguments": {
+          "additionalProperties": false,
+          "properties": {
+            "pattern": {
+              "maxLength": 64,
+              "minLength": 1,
+              "type": "string"
+            }
+          },
+          "required": [
+            "pattern"
+          ],
+          "type": "object"
+        },
+        "tool": {
+          "const": "get_pattern",
+          "type": "string"
+        }
+      },
+      "required": [
+        "tool",
+        "arguments"
+      ],
+      "type": "object"
+    },
+    {
+      "additionalProperties": false,
+      "properties": {
+        "arguments": {
+          "additionalProperties": false,
+          "properties": {},
+          "type": "object"
+        },
+        "tool": {
+          "const": "list_patterns",
+          "type": "string"
+        }
+      },
+      "required": [
+        "tool",
+        "arguments"
+      ],
+      "type": "object"
+    }
+  ]
+}

addedOutput schema / properties / results / items / properties / pattern
```
Added value: +{
+  "maxLength": 64,
+  "type": "string"
+}
```

changedOutput schema / properties / results / items / required

Previous value: -[
-  "path",
-  "url",
-  "title",
-  "snippet"
-]New value: +[
+  "path",
+  "url",
+  "title",
+  "snippet",
+  "next"
+]

1 tool updateOct 2, 2026

Changedreport_outcome11 fields changed

removedInput schema / properties / elapsed_milliseconds

Removed value: -{
-  "type": [
-    "integer",
-    "null"
-  ]
-}

removedInput schema / properties / input_tokens

Removed value: -{
-  "type": [
-    "integer",
-    "null"
-  ]
-}

removedInput schema / properties / model_id

Removed value: -{
-  "type": "string"
-}

removedInput schema / properties / model_precision

Removed value: -{
-  "enum": [
-    "exact",
-    "family"
-  ]
-}

addedInput schema / properties / note

Added value: +{
+  "maxLength": 280,
+  "type": "string"
+}

changedInput schema / properties / outcome / enum

Previous value: -[
-  "pass",
-  "fail",
-  "abandoned"
-]New value: +[
+  "worked",
+  "partly",
+  "did_not_work"
+]

removedInput schema / properties / output_tokens

Removed value: -{
-  "type": [
-    "integer",
-    "null"
-  ]
-}

removedInput schema / properties / task_class
```
Removed value: -{
-  "type": "string"
-}
```
removedInput schema / properties / tests_passed
```
Removed value: -{
-  "type": "integer"
-}
```

removedInput schema / properties / tests_ran

Removed value: -{
-  "type": "integer"
-}

changedInput schema / required

Previous value: -[
-  "ticket",
-  "model_id",
-  "task_class",
-  "outcome",
-  "tests_ran",
-  "tests_passed"
-]New value: +[
+  "ticket",
+  "outcome"
+]

1 tool updateSep 26, 2026

Changedsearch1 field changed

changedOutput schema / properties / match / enum

Previous value: -[
-  "all_words",
-  "any_word",
-  "none"
-]New value: +[
+  "all_words",
+  "any_word",
+  "none",
+  "empty"
+]

1 tool updateSep 24, 2026

Changedreport_outcome27 fields changed

removedInput schema / $schema

Removed value: -"https://json-schema.org/draft/2020-12/schema"

removedInput schema / properties / elapsed_milliseconds / anyOf

Removed value: -[
-  {
-    "maximum": 2678400000,
-    "minimum": 0,
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]

removedInput schema / properties / elapsed_milliseconds / description
```
Removed value: -"Omit when unknown."
```
addedInput schema / properties / elapsed_milliseconds / type
```
Added value: +[
+  "integer",
+  "null"
+]
```

removedInput schema / properties / input_tokens / anyOf

Removed value: -[
-  {
-    "maximum": 1000000000000,
-    "minimum": 0,
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]

removedInput schema / properties / input_tokens / description
```
Removed value: -"Omit when unknown; never guess 0."
```
addedInput schema / properties / input_tokens / type
```
Added value: +[
+  "integer",
+  "null"
+]
```

removedInput schema / properties / model_id / description

Removed value: -"The model that did the work, never an alias such as latest: its exact pin when known, otherwise its family (claude-sonnet) with model_precision family."

removedInput schema / properties / model_id / maxLength
```
Removed value: -128
```
removedInput schema / properties / model_id / minLength
```
Removed value: -1
```

removedInput schema / properties / model_precision / description

Removed value: -"exact (the default) or family. A family is accepted at lower confidence, counted apart from exact pins."

removedInput schema / properties / model_precision / type
```
Removed value: -"string"
```

removedInput schema / properties / outcome / description

Removed value: -"pass needs tests_ran > 0 and tests_passed = tests_ran."

removedInput schema / properties / outcome / type
```
Removed value: -"string"
```

removedInput schema / properties / output_tokens / anyOf

Removed value: -[
-  {
-    "maximum": 1000000000000,
-    "minimum": 0,
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]

removedInput schema / properties / output_tokens / description
```
Removed value: -"Omit when unknown; never guess 0."
```
addedInput schema / properties / output_tokens / type
```
Added value: +[
+  "integer",
+  "null"
+]
```

removedInput schema / properties / task_class / description

Removed value: -"The kind of work as {domain}.{task}, the domain one of coding, research, documents, reasoning, evaluation, operations, security: coding.bugfix, research.literature_review. A machine name, never a task description."

removedInput schema / properties / task_class / maxLength
```
Removed value: -128
```

removedInput schema / properties / task_class / pattern

Removed value: -"^(?:coding|research|documents|reasoning|evaluation|operations|security)(?:\\.[a-z][a-z0-9_]{0,31}){1,3}$"

removedInput schema / properties / tests_passed / maximum
```
Removed value: -1000000000
```
removedInput schema / properties / tests_passed / minimum
```
Removed value: -0
```
removedInput schema / properties / tests_ran / maximum
```
Removed value: -1000000000
```
removedInput schema / properties / tests_ran / minimum
```
Removed value: -0
```

removedInput schema / properties / ticket / description

Removed value: -"The ticket exactly as received (starts with \"ut1.\")."

removedInput schema / properties / ticket / maxLength
```
Removed value: -1024
```
removedInput schema / properties / ticket / minLength
```
Removed value: -1
```

1 tool updateSep 23, 2026

Changedreport_outcome6 fields changed

changedInput schema / properties / model_id / description

Previous value: -"The exact model identifier that did the work, never an alias."New value: +"The model that did the work, never an alias such as latest: its exact pin when known, otherwise its family (claude-sonnet) with model_precision family."

addedInput schema / properties / model_precision

Added value: +{
+  "description": "exact (the default) or family. A family is accepted at lower confidence, counted apart from exact pins.",
+  "enum": [
+    "exact",
+    "family"
+  ],
+  "type": "string"
+}

addedInput schema / properties / task_class / description

Added value: +"The kind of work as {domain}.{task}, the domain one of coding, research, documents, reasoning, evaluation, operations, security: coding.bugfix, research.literature_review. A machine name, never a task description."

removedInput schema / properties / task_class / enum
```
Removed value: -[
-  "coding.bugfix"
-]
```
addedInput schema / properties / task_class / maxLength
```
Added value: +128
```

addedInput schema / properties / task_class / pattern

Added value: +"^(?:coding|research|documents|reasoning|evaluation|operations|security)(?:\\.[a-z][a-z0-9_]{0,31}){1,3}$"

4 tool updatesSep 23, 2026

Changedlist_patterns1 field changed

addedInput schema / properties / domain

Added value: +{
+  "description": "Read the lens of one task domain instead; not together with a family.",
+  "enum": [
+    "coding",
+    "research",
+    "documents",
+    "reasoning",
+    "evaluation",
+    "operations",
+    "security"
+  ],
+  "type": "string"
+}

Changedlist_starters3 fields changed

addedInput schema / $schema

Added value: +"https://json-schema.org/draft/2020-12/schema"

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / task_class

Added value: +{
+  "description": "A task class such as coding.bugfix.",
+  "maxLength": 128,
+  "minLength": 1,
+  "type": "string"
+}

Changedreport_outcome6 fields changed

changedInput schema / properties / elapsed_milliseconds / description

Previous value: -"Wall time of the work; omit or null when unknown."New value: +"Omit when unknown."

changedInput schema / properties / input_tokens / description

Previous value: -"Omit or null when unknown; never guess 0."New value: +"Omit when unknown; never guess 0."

changedInput schema / properties / model_id / description

Previous value: -"The exact model identifier that did the work, never an alias like \"latest\"."New value: +"The exact model identifier that did the work, never an alias."

changedInput schema / properties / output_tokens / description

Previous value: -"Omit or null when unknown; never guess 0."New value: +"Omit when unknown; never guess 0."

removedInput schema / properties / task_class / description
```
Removed value: -"The task class of the work."
```

changedInput schema / properties / ticket / description

Previous value: -"The Use-Ticket header value, exactly as received (starts with \"ut1.\")."New value: +"The ticket exactly as received (starts with \"ut1.\")."

Changedsearch3 fields changed

changedInput schema / properties / query / description

Previous value: -"Words to look for, such as \"orchestrator worker\" or \"debate\"."New value: +"Words to look for, such as \"orchestrator worker\", \"verification\" or \"coding\"."

addedOutput schema / properties / match

Added value: +{
+  "enum": [
+    "all_words",
+    "any_word",
+    "none"
+  ],
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "results"
-]New value: +[
+  "match",
+  "results"
+]

1 tool updateSep 23, 2026
- Addedreport_outcome
5 tool updatesSep 23, 2026
- First observedfetch
- First observedget_pattern
- First observedlist_patterns
- First observedlist_starters
- First observedsearch

Related MCP Connectors

changegamer A
io.github.beneb89
Agent-first resource directory for AI agents: protocols, security, RAG, memory, evals, and more.
RAG Systems Knowledge & Memory Agent Orchestration
142
https://changegamer.ai/mcp
OriginGrid A
net.origingrid
AI Agent Source Registry. 288K+ curated sources for agentic search and discovery.
Search Agent Orchestration
1
https://www.origingrid.net/mcp
Awareness — Memory, Knowledge & Agent Markets A
market.awareness
Memory + public knowledge graph for AI agents: 1,000+ sourced papers, deal board, agent market.
Knowledge & Memory RAG Systems Research & Data
191
https://awareness.market/mcp
Agentic Atlas A
dev.agentic-atlas
Patterns for designing and reviewing AI skills, agents, and multi-agent workflows. Find guidance on context economy, delegation, verification, and tool design; inspect claims, worked examples, maturity labels, and source references. Five read-only tools let agents discover relevant patterns, compare concise cards, read specific sections, and explore relationships. Hosted Streamable HTTP at https://agentic-atlas.dev/mcp/ — no installation, account, or API key required. Browse the atlas at https://agentic-atlas.dev/.
Agent Orchestration Developer Tools Software Architecture
51
https://agentic-atlas.dev/mcp/

Related MCP Servers

OmniAgent MCP Mesh
Agent Orchestration Autonomous Agents Knowledge & Memory
ASHOKMUKHERJEE6
A
license
Not graded
quality
D
maintenance
Enterprise-grade asynchronous multi-agent orchestration and MCP router mesh framework, enabling DAG-based workflows, consensus-driven agent swarms, and REST/telemetry gateway.
Updated 3 months ago (2026-07-31 18:32 UTC)
MIT
boardroom-mcp
Autonomous Agents Knowledge & Memory
randysalars
A
license
A
quality
D
maintenance
Multi-advisor debate, institutional memory, trust scoring, and cognitive governance for AI agents, all running locally.
Updated a month ago (2026-10-01 21:13 UTC)
5
12 npm
1
MIT
DiviDen MCP Server
Autonomous Agents Agent Orchestration Communication
Denominator-Ventures
A
license
Not graded
quality
C
maintenance
Open coordination network for AI agents and their humans. 13 tools for structured coordination, job marketplace, reputation system. Dual-protocol: MCP + A2A. MIT licensed.
Updated 5 months ago (2026-06-04 05:53 UTC)
1
MIT
MIDAS
Autonomous Agents Command Line
omarkhandji-commits
A
license
Not graded
quality
C
maintenance
Local-first AI agent for approval-gated automation and verifiable LLM workflows.
Updated 3 months ago (2026-07-31 18:35 UTC)
1
MIT

Try in Browser

Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?